System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving input market data, investor targeting information, and historical promotion cases; means for pre-processing the input data; means for extracting features from the pre-processed data; means for applying behavioral economics theory to generate a promotion offer for the extracted features; and means for outputting the promotion offer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern companies, salespeople, marketers, analysts, and others are required to interpret market data, investor relations information, and past sales promotion examples to make effective proposals to clients and within their own companies. However, proposals often tend to be superficial, or simply consist of a list of data, making it difficult to understand what they are trying to communicate. Another issue is the lack of clear methods for inducing consumer behavior. Therefore, it is necessary to uncover latent consumer needs, intensify competition between companies, and promote value creation for companies. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including: means for receiving input market data, investor information, and past sales promotion examples; means for preprocessing the input data; means for extracting features from the preprocessed data; means for generating sales promotion proposals for the extracted features by applying theories of behavioral economics; and means for outputting the sales promotion proposals. This makes it possible to interpret data and make proposals more persuasive, enabling effective proposals from the perspective of consumer behavior, leading to actual consumption behavior and increased sales. Specifically, the system further includes means for analyzing the preprocessed data, performing statistical analysis and clustering, and detecting patterns, and further applying theories of behavioral economics such as prospect theory, social proof, and the anchoring effect to generate sales promotion proposals that are optimal for consumers.

[0006] "Market Data" means data that includes information such as sales, sales volume, and trends in a particular market.

[0007] "Investor relations information" refers to information provided to investors, such as a company's financial situation, performance forecast, and management strategy.

[0008] "Sales promotion cases" are data on the status and results of past sales promotion activities and campaigns.

[0009] "Input" is the operation or act of entering data into a system.

[0010] "Preprocessing" is the process of removing unnecessary information and formatting the input data in order to make effective use of it.

[0011] "Feature extraction" is the process of finding important patterns or characteristics in data.

[0012] "Behavioral economics" is a branch of economics that deals with how people make decisions and incorporates insights from psychology.

[0013] A "sales promotion proposal" is a proposal that outlines strategies and ideas for increasing sales of a particular product or service.

[0014] "Output" is the operation or act of extracting information from a system.

[0015] "Statistical analysis" is a method of analyzing data numerically to derive mean values, variances, correlations, etc.

[0016] "Clustering" is a technique for grouping data based on specific characteristics.

[0017] "Pattern detection" is the task of finding specific patterns or trends in data.

[0018] Prospect theory is a theory that explains the decision-making process people go through when making risky choices.

[0019] "Social proof" is the phenomenon in which observing the behavior of others helps us make informed decisions about our own behavior.

[0020] The "anchoring effect" is a phenomenon in which people are strongly influenced by the information they are presented with initially, and their subsequent judgments and actions are based on that information. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] The present invention is a system that inputs market data, investor information, past sales promotion examples, etc., preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Specific embodiments for implementing the present invention will be described below.

[0043] 1. Data input:

[0044] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[0045] 2. Data preprocessing:

[0046] The server receives the input data and performs preprocessing, including cleaning the data, standardizing the format, filling in missing values, and normalizing the data, thereby ensuring the consistency and reliability of the data.

[0047] 3. Data analysis and feature extraction:

[0048] The server then analyzes the pre-processed dataset and extracts key features using techniques such as statistical analysis, clustering, and pattern detection, which can reveal, for example, the behavioral patterns and purchasing tendencies of specific consumer groups within a target market.

[0049] 4. Application of behavioral economics theory:

[0050] The server applies behavioral economics theory to the extracted features, specifically generating promotional offers based on prospect theory, social proof, anchoring effects, etc. These offers are intended to encourage consumer behavior and motivate purchases.

[0051] 5. Generate promotional offers:

[0052] The server generates specific sales promotion proposals based on the data analysis and behavioral economics theory. These proposals include what promotional methods should be used, the reasons for using them, and the expected effects. For example, they could propose a discount campaign for the first purchase of a new health food product, or an advertising message targeted at a specific target group.

[0053] 6. Proposal Development:

[0054] The user then makes a presentation to a retailer or an in-house marketing team based on the sales promotion proposals provided by the server. The proposals are well-grounded in theoretical background and concrete data, making them highly persuasive.

[0055] Example scenario

[0056] scenario:

[0057] A user is trying to bring a new health food product to market.

[0058] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[0059] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[0060] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[0061] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[0062] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[0063] The user then uses the proposals provided by the server to make detailed presentations to retail clients and internal marketing teams.

[0064] As described above, the present invention supports the formulation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] Users use terminals to input market data, investor relations information, past sales promotion cases, etc. Data formats include CSV files, Excel sheets, and database connections.

[0068] Step 2:

[0069] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[0070] Step 3:

[0071] The server handles data formatting, including standardizing date formats, normalizing numeric data, and tokenizing text data.

[0072] Step 4:

[0073] The server normalizes the data to ensure consistency across different data sets, for example by scaling each data set to a consistent value range.

[0074] Step 5:

[0075] The server analyzes the preprocessed data set, specifically calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[0076] Step 6:

[0077] The server performs clustering to classify consumer groups based on their characteristics, for example using the K-means algorithm to group similar consumers.

[0078] Step 7:

[0079] The server performs pattern detection and analyses for trends and correlations over time, including time series analysis and calculation of correlation matrices.

[0080] Step 8:

[0081] The server extracts important features, which includes generating new features, transforming existing features, and selecting important features based on feature importance.

[0082] Step 9:

[0083] The server applies behavioral economics theories to the extracted features to generate recommendations based on prospect theory, social proof, anchoring effect, etc.

[0084] Step 10:

[0085] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0086] Step 11:

[0087] The user receives the proposal provided by the server on the terminal and makes a presentation to the retailer or the company's internal marketing team.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] In conventional sales promotion systems, the processes of data input, preprocessing, analysis, and the generation of sales promotion proposals based on the analysis results were carried out independently, resulting in a lack of consistency and efficiency. Furthermore, it was difficult to automatically generate specific sales promotion proposals based on theories of behavioral economics, which required time and effort from the user. These issues made it difficult to develop a fast and effective sales promotion strategy.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes means for allowing a user to input market data, investor information, and past sales promotion examples using a terminal, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, and means for outputting the sales promotion proposals to the user. This makes it possible to perform the entire process from data input to the generation of sales promotion proposals as a single integrated process, enabling the formulation of a rapid and effective sales promotion strategy.

[0093] "User" refers to the person who operates the system and inputs information such as market data, investor information, and past promotional cases through a terminal.

[0094] "Terminal" refers to a device through which a user inputs data and which acts as an interface to the system.

[0095] "Market data" refers to basic information related to sales promotion, such as market trends, consumer behavior patterns, and economic indicators.

[0096] "Investor information" refers to a company's financial information, management strategy, performance forecasts, etc. provided to investors.

[0097] "Past sales promotion examples" refers to specific examples of sales promotion activities that have been implemented to date and their results.

[0098] "Server" refers to a central processing unit that pre-processes input data, performs data analysis, and generates promotional offers.

[0099] "Data preprocessing" refers to a series of processes to improve data quality, such as cleaning input data, standardizing formats, imputing missing values, and data normalization.

[0100] "Feature extraction" refers to the process of extracting important patterns and trends from pre-processed data.

[0101] "Behavioral economics" refers to theories that explain the psychological and social factors that influence human behavior and decision-making, such as prospect theory, social proof, and the anchoring effect.

[0102] "Sales promotion proposal" refers to a proposal that shows specific sales promotion methods and their effectiveness based on data analysis and behavioral economics theory.

[0103] "Output" refers to displaying the generated promotional offers to the user.

[0104] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Detailed embodiments of this system are described below.

[0105] Hardware and software used

[0106] Users use devices to input market data, investor relations information, and past sales promotions. Devices can be PCs, tablets, smartphones, etc. Input data can be in the form of CSV files, Excel sheets, or database connections.

[0107] The server preprocesses the received data, cleaning it, standardizing its format, imputing missing values, and normalizing it, using programming languages ​​such as Python and R and libraries such as Pandas and Numpy.

[0108] Based on the preprocessed dataset, the server performs data analysis such as statistical analysis, clustering, and pattern detection using machine learning libraries such as Scikit-learn and TensorFlow.

[0109] The server applies behavioral economics theories—specifically, prospect theory, social proof, and the anchoring effect—to generate promotional offers. The proposal generation incorporates NLP (natural language processing) techniques and leverages generative AI models, such as OpenAI's GPT-3 or BERT models.

[0110] Example scenario

[0111] scenario:

[0112] Consider a case where a user is trying to bring a new health food product to market.

[0113] 1. The user uses a terminal to input past sales data for health foods, examples of competitors' sales promotions, and consumer demographic information for the target market into the system. The input data is uploaded in Excel file format.

[0114] 2. The server receives the uploaded data and performs data cleaning. If an invalid data format is detected, it is recorded in an error log and corrected as much as possible. If missing values ​​are found, they are imputed using the mean or median.

[0115] 3. The server analyzes the preprocessed dataset and extracts important features. For example, a pattern may emerge: women in their 30s tend to prefer high-protein foods. Statistical analysis and clustering then clarify trends within the target customer group.

[0116] 4. The server applies behavioral economics theory to propose strategies using discount campaigns based on prospect theory and social proof citing competitor success stories. AI models are applied to automatically generate proposals.

[0117] 5. The server generates specific sales promotion proposals such as "discount campaigns for first-time purchases of health foods" or "advertising messages for specific target groups" and outputs them to the user.

[0118] Based on the sales promotion proposals provided by the server, users can make detailed presentations to retailers and in-house marketing teams. The proposals contain both theoretical background and concrete data-based justification, making them highly persuasive.

[0119] Prompt Sentence Examples

[0120] Example 1:

[0121] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[0122] Example 2:

[0123] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[0124] Generative AI model used

[0125] The system uses generative AI models such as OpenAI's GPT-3 and BERT to generate promotional offers, leveraging advanced natural language generation capabilities to provide users with effective and persuasive promotional strategies.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Step 1:

[0128] A user uses a terminal to input market data, investor relations information, and past sales promotion cases into the system. This input data is provided as a CSV file, Excel spreadsheet, etc. For example, a user selects an Excel file and clicks the upload button on the terminal to send the data to the system.

[0129] Input: Market data, investor relations information, and past promotions provided in the form of CSV files, Excel sheets, database connections, etc.

[0130] Output: Input data sent to the server

[0131] Step 2:

[0132] The server preprocesses the data received. Specifically, it performs processes such as data cleaning, format standardization, missing value imputation, and data normalization. If an invalid data format is detected, it records it in the error log and attempts to correct it if possible. If missing values ​​are found, they are imputed with the mean or median.

[0133] Input: Input data sent by the user

[0134] Output: Cleaned and uniformly formatted pre-processed data

[0135] Step 3:

[0136] The server analyzes the preprocessed data. Analysis methods include statistical analysis, clustering, and pattern detection. This reveals patterns of consumer behavior and market trends. For example, the server might extract a pattern that women in their 30s prefer high-protein foods.

[0137] Input: Preprocessed data

[0138] Output: Analysis results and important feature data

[0139] Step 4:

[0140] The server applies behavioral economics theory based on the analysis results. For example, it uses prospect theory, social proof, and the anchoring effect to generate effective sales promotion proposals. It utilizes generative AI models to automatically propose strategies to encourage consumer behavior.

[0141] Input: Analysis results and important feature data

[0142] Output: Sales promotion proposals based on the theory of behavioral economics

[0143] Step 5:

[0144] The server outputs the generated sales promotion proposal to the user. This proposal includes the promotional method to be used, the reasons for it, and the expected effects. The user then uses this proposal to make a presentation to a retailer or an internal marketing team. For example, the server might propose a "discount campaign for the first purchase of health foods" and simulate its effects.

[0145] Input: Sales promotion proposals based on the theory of behavioral economics

[0146] Output: Promotional offers provided to the user

[0147] Prompt Sentence Examples

[0148] Example 1:

[0149] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[0150] Example 2:

[0151] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[0152] (Application example 1)

[0153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0154] While conventional sales promotion proposal systems are useful in generating proposals based on data analysis and behavioral economics theory, they lack a means to directly provide proposals based on consumer behavior and purchasing trends in real time. As a result, it is difficult to carry out immediate sales promotion activities in stores, and sales promotions cannot be carried out at the optimal time.

[0155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0156] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals in real time, and means for outputting sales promotion proposals based on consumer behavior and purchasing trends in real time using a smart device. This makes it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[0157] "Market data" refers to information about market trends, competitive situations, consumer preferences and purchasing patterns, etc.

[0158] "Investor relations information" refers to information about a company's performance and strategies that is provided to investors.

[0159] "Past sales promotion cases" is information about the content and results of sales promotion activities carried out in the past.

[0160] "Data preprocessing" is the process of converting raw data into an analyzable form, including data cleaning, imputation of missing values, and normalization.

[0161] "Feature extraction" is the process of finding significant patterns and trends in a data set.

[0162] "Behavioral economics" is a science that analyzes economic behavior by taking into account psychological factors and is a theory that influences consumer decision-making.

[0163] "Prospect theory" is a theory that explains how people make decisions in risky situations.

[0164] "Social proof" is a psychological phenomenon in which people base their own behavior on the behavior of others.

[0165] The "anchoring effect" is a phenomenon in which the first information presented has a strong influence on subsequent decision-making.

[0166] "Real-time" means that processing is done instantly and results are obtained almost immediately.

[0167] "Sales promotion proposals" are specific methods and strategies for increasing consumer purchasing motivation.

[0168] A "smart device" is a device that has internet connectivity and can process and display a variety of information.

[0169] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. A detailed description of an embodiment of the present invention will be given below.

[0170] The system consists of the following stages:

[0171] 1. Data input

[0172] Users use terminals to input market data, investor relations information, and past promotions into the system, which is provided via CSV files, Excel sheets, or database connections.

[0173] 2. Data Preprocessing

[0174] The server receives the input data and performs preprocessing, which includes data cleaning, formatting standardization, missing value imputation, and data normalization. Specifically, data cleaning is performed using the Python Pandas library, and data normalization is performed using Scikit-learn.

[0175] 3. Data analysis and feature extraction

[0176] The server analyzes the pre-processed dataset and extracts key features using statistical analysis, clustering (e.g., K-means), and pattern detection. This process identifies behavioral patterns and purchasing trends among consumer groups.

[0177] 4. Application of behavioral economics theory

[0178] The server applies behavioral economics theory to the extracted features, specifically prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer behavior and increase purchasing intent.

[0179] 5. Generate promotional offers

[0180] The server generates specific sales promotion proposals based on the above data analysis and behavioral economics theory. These proposals are output in real time via smart devices (e.g., smart glasses). For example, if a store clerk is wearing smart glasses, appropriate sales promotion proposals will be instantly displayed based on the customer's behavioral patterns.

[0181] 6. Proposal Development

[0182] Users can carry out sales promotion activities in real time at the store based on sales promotion proposals provided by the server. In a specific example, a store clerk wearing smart glasses receives a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately provides that information to the customer.

[0183] Prompt Sentence Examples

[0184] "Generate real-time promotional offers using the following data:

[0185] Market Data

[0186] Investor information

[0187] Past promotional examples

[0188] The generated recommendations should be based on behavioral economics theory (e.g., prospect theory). They should demonstrate effectiveness for specific consumer groups and provide specific examples of sales strategies. The output should be in the following format:

[0189] {

[0190] "promotion_type": "discount",

[0191] "message": "Your 10% discount on our new protein bars is valid.",

[0192] "expected_effect": "Increased willingness to purchase"

[0193] }

[0194] "

[0195] As a result, the present invention systemizes a series of processes from data input to proposal creation and deployment, making it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[0196] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0197] Step 1:

[0198] Users use a terminal to input market data, investor relations information, and past promotions. Specifically, they upload the data to the system via a CSV file, Excel spreadsheet, or database connection. The input of this process is market data, investor relations information, and past promotions, and the output is that this data is stored on the server.

[0199] Step 2:

[0200] The server receives the input data and performs preprocessing. Specifically, it performs the following data processing: data cleaning, format standardization, missing value imputation, and data normalization. For example, it uses the Pandas library to impute missing values ​​and Scikit-learn to normalize the data. The input of this process is the input raw data, and the output is cleaned and normalized data.

[0201] Step 3:

[0202] The server analyzes the preprocessed data and extracts features. Specifically, it performs statistical analysis and clustering (e.g., K-means) to identify behavioral patterns and purchasing tendencies of consumer groups. For example, K-means clustering is used to identify target groups. The input of this process is the preprocessed data, and the output is consumer behavior patterns and features.

[0203] Step 4:

[0204] The server applies behavioral economics theory to the extracted features. Specifically, it generates recommendations using prospect theory, social proof, and the anchoring effect. For example, it uses prospect theory to recommend a "limited-time discount." The input to this process is the extracted feature data, and the output is a recommendation based on behavioral economics.

[0205] Step 5:

[0206] The server generates specific sales promotion proposals based on the theory of behavioral economics. The proposals include plans to be output in real time via smart devices (e.g., smart glasses). Specifically, the server outputs the generated sales promotion proposals in JSON format and sends them to the smart devices. The input of this process is the proposals based on behavioral economics, and the output is the real-time sales promotion proposals.

[0207] Step 6:

[0208] Based on the sales promotion proposals provided by the server, users can carry out sales promotion activities in real time at the store. For example, a sales clerk wearing smart glasses can receive a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately convey that information to the customer. The input to this process is the real-time sales promotion proposal sent from the server, and the output is the implementation of the sales promotion activity for the customer.

[0209] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0210] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments for implementing the present invention will be described below.

[0211] 1. Data input:

[0212] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[0213] 2. Data preprocessing:

[0214] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[0215] 3. Standardize data formats:

[0216] The server unifies the data format by unifying date formats, standardizing numeric data, tokenizing text data, etc.

[0217] 4. Data normalization:

[0218] The server normalizes the preprocessed data to ensure consistency across different datasets, for example by scaling each data set to a uniform value range.

[0219] 5. Data analysis and feature extraction:

[0220] The server analyzes the preprocessed dataset and performs basic statistical calculations, clustering, pattern detection, etc. to understand the basic characteristics of the data. It selects important features and reveals consumer behavior patterns and purchasing trends.

[0221] 6. Application of behavioral economics theory:

[0222] The server generates suggestions based on the extracted features, such as prospect theory, social proof, and anchoring effect, which can encourage consumer behavior and increase purchasing motivation.

[0223] 7. Incorporating an Emotion Engine:

[0224] The server recognizes the user's emotions using an emotion engine. The emotion engine detects the user's emotions using at least one of voice analysis, text analysis, and facial expression analysis. For example, the server collects real-time emotion data while the user is giving a presentation.

[0225] 8. Leveraging Emotional Data:

[0226] The server customizes the suggestions based on the user's emotional data, recognized by the emotion engine. If the user is expressing positive emotions, the server emphasizes optimistic suggestions. Conversely, if the user is expressing negative emotions, the server adds information to address concerns.

[0227] 9. Promotional Offer Generation:

[0228] The server generates specific promotional proposals based on the data analysis, application of behavioral economics theory, and sentiment data, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0229] 10. Proposal Development:

[0230] The user receives the proposals provided by the server on their device and makes presentations to retailers or their internal marketing teams. The proposals are customized based on emotional data, making them more persuasive to the target audience.

[0231] Example scenario

[0232] scenario:

[0233] A user is trying to bring a new health food product to market.

[0234] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[0235] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[0236] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[0237] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[0238] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[0239] The server uses an emotion engine to collect real-time emotional data from users during a presentation. For example, if a user has a positive reaction, the server can emphasize the content of the proposal in line with that emotion.

[0240] The user then uses the server-provided customized proposal to make detailed presentations to retailers and internal marketing teams.

[0241] As described above, the present invention supports the creation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals and by customizing them based on the user's emotions.

[0242] The processing flow will be explained below.

[0243] Step 1:

[0244] Users use terminals to input market data, investor relations information, and past promotional cases into the system, which can be provided in the form of CSV files, Excel spreadsheets, database connections, etc.

[0245] Step 2:

[0246] The server receives the input data and performs data cleaning, specifically by completing missing values, removing noise, and eliminating invalid data to improve the quality of the data.

[0247] Step 3:

[0248] The server handles data formatting, including standardizing date formats, standardizing numeric data, and tokenizing text data.

[0249] Step 4:

[0250] The server normalizes the data, scaling each data set to a consistent value range for consistency across different data sets.

[0251] Step 5:

[0252] The server analyzes the preprocessed dataset, calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[0253] Step 6:

[0254] The server performs clustering to classify consumer groups based on their characteristics, specifically by using the K-means algorithm to group similar consumers.

[0255] Step 7:

[0256] The server performs pattern detection, analyzing trends and correlations over time, and uncovering hidden patterns in the data through time series analysis and calculation of correlation matrices.

[0257] Step 8:

[0258] The server extracts important features, generates new features, transforms existing features, and selects the most important features using Feature Importance.

[0259] Step 9:

[0260] The server applies behavioral economics theories, such as prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer action.

[0261] Step 10:

[0262] The server recognizes the user's emotions using an emotion engine, which detects the user's emotions using voice analysis, text analysis, or facial expression analysis.

[0263] Step 11:

[0264] The server customizes the suggestions based on the user's emotional data. For example, if the user is expressing positive emotions, it will emphasize optimistic information, and if the user is expressing negative emotions, it will provide information that emphasizes safety and reliability.

[0265] Step 12:

[0266] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0267] Step 13:

[0268] The user receives the proposal information provided by the server on their device and makes a presentation to their retailer or in-house marketing team. The proposal information is customized based on emotional data, making it more persuasive to the target audience.

[0269] Example 2

[0270] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0271] Conventional sales promotion systems are limited to simple data analysis, and have limitations in predicting consumer behavior and generating effective proposals. Furthermore, proposals lack persuasiveness and effectiveness because they are not customized to take user emotions into account. To solve this problem, a system is needed that precisely analyzes input data, generates proposals based on theories of behavioral economics, and further customizes proposals by recognizing user emotions in real time.

[0272] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting market data, investor information, and past sales promotion cases and preprocessing the data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for recognizing user emotions and customizing the sales promotion proposals, and means for outputting the customized sales promotion proposals. This makes it possible to generate advanced and effective sales promotion proposals based on the input data and further customize the proposals according to the user's emotions.

[0273] "Market data" is information about market movements, trends, sales, consumer behavior, etc.

[0274] "Investor relations information" refers to information provided to investors, such as a company's financial situation, performance forecasts, and investment risks.

[0275] "Sales promotion cases" refers to information about the content, results, effects, etc. of sales promotion activities that have been carried out in the past.

[0276] "Data preprocessing" is the process of preparing input data for analysis by filling in missing values, removing noise, and excluding invalid data.

[0277] "Feature extraction" is a data analysis technique for finding useful patterns and trends in pre-processed data.

[0278] "Behavioral economics theory" is a theory that explains human psychology and behavior in economic activities, and includes prospect theory, social proof, and the anchoring effect.

[0279] A "sales promotion proposal" is a concrete presentation of strategies and ideas for promoting sales.

[0280] "Means for recognizing emotions" refers to technology that detects a user's emotions using voice analysis, text analysis, facial expression analysis, etc.

[0281] "Means for customizing suggestions" refers to technology that adjusts and adapts suggestions based on the user's emotional data.

[0282] "Data analysis" refers to techniques such as statistical analysis and clustering that are used to extract useful information from data.

[0283] "Statistical analysis" is a statistical method for understanding the distribution and trends of data.

[0284] "Clustering" is an analytical technique for classifying data into similar groups.

[0285] "Prospect theory" is a theory that explains how people evaluate gains and losses.

[0286] "Social proof" is a psychological phenomenon in which people base their decisions on the behavior and success stories of others.

[0287] The "anchoring effect" is a phenomenon in which initially presented information has a strong influence on subsequent decision-making.

[0288] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments of the present invention are described below.

[0289] 1. Data input

[0290] Users use a terminal to input market data, investor relations information, and past sales promotions into the system. Input data can be provided in the form of CSV files, Excel spreadsheets, or database connections, allowing users to easily utilize existing data resources to provide data to the system.

[0291] 2. Data Preprocessing

[0292] The server receives the input data and performs data cleaning using the Python Pandas library. Specifically, it imputes missing values, removes noise, and eliminates invalid data. This preprocessing step improves the quality of the data and increases the reliability of the subsequent analysis results.

[0293] 3. Standardization of data formats

[0294] The server standardizes the date format of the cleaned data to "YYYY-MM-DD" and uses Scikit-learn's scaling library to normalize numeric data. It also uses NLP tools to tokenize text data and convert it into a unified format, making the data consistent and easier to analyze.

[0295] 4. Data Normalization

[0296] The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1. This normalization step ensures consistency between different datasets, making them easier to compare.

[0297] 5. Data analysis and feature extraction

[0298] The server analyzes the preprocessed dataset, calculates basic statistics, and uses clustering algorithms (e.g., K-means clustering) to detect patterns and identify consumer behavior and purchasing trends. It then selects important features to help predict consumer behavior and develop marketing strategies.

[0299] 6. Application of behavioral economics theory

[0300] The server applies behavioral economics theories such as prospect theory, social proof, and anchoring effect to generate sales promotion proposals for the extracted features. For example, it is possible to stimulate consumer purchasing motivation by proposing a "limited-time discount promotion."

[0301] 7. Incorporating and utilizing an emotional engine

[0302] The server recognizes the user's emotions using an emotion engine. The emotion engine detects emotions in real time using voice analysis, text analysis, or facial expression analysis. The server customizes the suggestions based on the user's emotion data, emphasizing optimistic suggestions when the user shows positive emotions, and adding information to cover concerns when the user shows negative emotions.

[0303] 8. Promotional proposal generation and deployment

[0304] The server generates sales promotion proposals based on data analysis, behavioral economics theory, and emotional data. Specific examples include campaign design, advertising message creation, and product placement optimization. Users receive the proposals provided by the server on their devices and present them to clients or their internal marketing teams. Customized proposals based on emotional data can increase persuasiveness.

[0305] Example scenario

[0306] If a user is trying to bring a new health food product to market, the following prompt text could be used:

[0307] Example prompt sentence:

[0308] "Generate a sales promotion strategy for a high-protein food product targeted at women in their 30s. Using past sales data and competitor examples as a reference, create a proposal by applying prospect theory."

[0309] As described above, the present invention supports the development of more effective sales promotion strategies by systematizing a series of processes from data input to proposal creation and development, and by customizing based on the user's emotions.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1:

[0312] Input: Users use terminals to upload market data, investor relations information, and past promotional cases into the system.

[0313] Specific operation: The user selects a CSV file or Excel sheet on the device and clicks the "Import" button.

[0314] Output: The server receives the input data and stores it in its internal database.

[0315] Step 2:

[0316] Input: The server retrieves the input data.

[0317] Specific operation: The server reads data from the database and performs data cleaning using Python's Pandas library.

[0318] Output: Cleaned data with missing values ​​imputed and noise and incorrect data removed.

[0319] Step 3:

[0320] Input: Cleaned data.

[0321] What it does: The server standardizes the date format to "YYYY-MM-DD", applies Scikit-learn's scaling library to normalize numeric data, and tokenizes text data using NLP tools.

[0322] Output: Uniformly formatted data.

[0323] Step 4:

[0324] Input: Uniformly formatted data.

[0325] What it does: The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1.

[0326] Output: Normalized data.

[0327] Step 5:

[0328] Input: Normalized data.

[0329] What it does: The server calculates basic statistics and uses the K-means clustering algorithm to find patterns in the data.

[0330] Output: Clustering results and feature extracted data.

[0331] Step 6:

[0332] Input: Feature extracted data.

[0333] What happens: The server applies prospect theory, social proof, and anchoring effects to generate promotional offers.

[0334] Output: Promotion proposal.

[0335] Step 7:

[0336] Input: Promotion offers and user interaction data.

[0337] How it works: The server uses an emotion engine to recognize the user's emotions in real time, using either voice analysis, text analysis, or facial expression analysis.

[0338] Output: User emotion data.

[0339] Step 8:

[0340] Input: Promotional offers and user sentiment data.

[0341] What happens: The server customizes promotional offers based on the user's emotions.

[0342] Output: A customized promotional offer.

[0343] Step 9:

[0344] Input: Customized promotional offer.

[0345] Specific operations: The server generates detailed specific proposals such as campaign design, advertising message creation, and product placement optimization.

[0346] Output: Final promotion proposal.

[0347] Step 10:

[0348] Input: Final promotion proposal.

[0349] Specific operation: The user receives the proposal from the server and uses the terminal to present it to clients or the internal marketing team.

[0350] Output: A customized promotional offer for presentation.

[0351] (Application example 2)

[0352] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0353] Conventional sales promotion systems were unable to analyze customer emotions and behavior in real time and make immediate proposals based on that analysis. This made it difficult to provide optimal sales strategies tailored to customer needs and emotions in a timely manner, limiting the effectiveness of sales promotions. In particular, in brick-and-mortar stores, it is necessary to quickly and accurately understand the emotions of each individual customer and make proposals based on that information, making it urgent to solve this problem.

[0354] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0355] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals, means for recognizing customer emotions in real time, and means for customizing the proposal content based on the recognized emotion data. This makes it possible to grasp customer emotions in real time in a physical store and instantly make optimal sales promotion proposals based on the customer emotions.

[0356] "Market data" refers to information such as market movements and trends, sales data, and consumer behavior.

[0357] "Investor information" refers to information necessary for investors to make decisions, such as stock prices, investment risks, and corporate performance.

[0358] "Past sales promotion examples" refers to information about the implementation and effectiveness of past promotions and campaigns.

[0359] "Preprocessing" refers to tasks such as data cleaning, filling in missing values, and standardizing formats to convert input data into a format that is easy to analyze.

[0360] "Feature extraction" refers to the process of finding important patterns and trends from preprocessed data that are useful for data analysis and machine learning.

[0361] "Behavioral economics" refers to a field of study that combines psychology and economics to study the decision-making motivations and behavior of consumers and investors.

[0362] Prospect theory is a theory that explains why consumers behave differently depending on whether they are gaining or losing something, and is based on differences in the evaluation of risks and benefits.

[0363] "Social proof" is a theory that explains consumer psychology, in which people base their own behavior on the behavior of others.

[0364] The "anchoring effect" is a theory that explains people's tendency to base subsequent judgments on the information they first receive.

[0365] "Emotion recognition" refers to technology that identifies a user's emotions in real time through voice analysis, text analysis, facial expression analysis, etc.

[0366] "Sales promotion proposals" refer to proposals that scientifically derive promotional campaigns and advertising messages for specific products or services in order to carry out marketing activities effectively.

[0367] In order to implement the present invention, the following system must be constructed.

[0368] First, the server has a means of receiving input market data, investor relations information, and past sales promotion cases. This means can import data in a variety of formats, such as CSV files, Excel sheets, and database connections, making it easy for users to input the data they need.

[0369] The server then has the means to preprocess the input data, cleaning it, imputing missing values, removing noise, filtering out invalid data, etc. This process can be automated using Python scripts.

[0370] Furthermore, statistical analysis, clustering, and pattern detection are performed to extract features from the preprocessed data. This allows us to understand the basic features of the data and reveal consumer behavior patterns and purchasing trends. The tools used are Python libraries (e.g., Pandas, Scikit-learn).

[0371] The system applies behavioral economics theory, such as prospect theory, social proof, and the anchoring effect, to generate sales promotion proposals based on data analysis results. This proposal generation can be achieved using an algorithm built in Python.

[0372] The invention also incorporates a means for recognizing users' emotions in real time. This involves using a camera and microphone in the smart glasses to capture the customer's facial expressions and voice, and then analyzing the data with an emotion recognition engine such as Microsoft Azure Face API. Based on the emotional data recognized at this stage, the system can customize the recommendations.

[0373] The results of this data processing and analysis are displayed on the smart glasses' display in real time, enabling prompt sales promotion proposals. Finally, the proposals output from the system can be used by users when making presentations to retailers or their internal marketing teams.

[0374] Examples:

[0375] For example, when a salesperson at a shoe store puts on smart glasses and starts serving customers, the following flow is assumed.

[0376] 1. A store clerk puts on the smart glasses and begins interacting with the customer.

[0377] 2. The smart glasses capture the customer's facial expressions and voice, and the data is sent to the server.

[0378] 3. Emotion recognition is performed in real time on the server, and the results are sent back to the smart glasses.

[0379] 4. Based on past data and behavioral economics theory, the server will suggest "new sports shoes" to customers who show positive emotions.

[0380] 5. The suggestions are displayed on the smart glasses' display, and the store clerk uses them to suggest appropriate products.

[0381] Prompt Sentence Examples

[0382] Customer sentiment analysis results: Positive

[0383] Past data analysis results: New sports shoes are effective for customers who show positive emotions

[0384] Suggestion: Recommend new sports shoes

[0385] This makes it possible for brick-and-mortar stores to instantly make optimal sales promotion proposals that reflect the customer's emotions.

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] The server receives market data, investor relations information, and past promotional examples from users in the form of CSV files, Excel spreadsheets, or database connections. The server loads this data into memory and creates an input dataset.

[0389] Step 2:

[0390] The server preprocesses the input data. This process includes data cleaning (filling in missing values, removing noise, and eliminating invalid data). Specifically, the dataset is prepared using a Python script. The input is the input data, and the output is the cleaned dataset.

[0391] Step 3:

[0392] The server converts the cleaned data into a unified format, which includes unifying date formats, normalizing numeric data, and tokenizing text data. The input is the cleaned dataset, and the output is the unified dataset.

[0393] Step 4:

[0394] The server analyzes the unified data set, calculates basic statistics, performs clustering, and detects patterns. Specifically, it performs data analysis using Python's Pandas and Scikit-learn. The input is the unified data set, and the output is the analysis results.

[0395] Step 5:

[0396] The server extracts features based on the results of data analysis. It selects important features to clarify consumer behavior patterns and purchasing trends. The input is the analysis results, and the output is the feature extraction results.

[0397] Step 6:

[0398] The server applies behavioral economics theory to the feature extraction results to generate promotional offers. Specifically, it uses an algorithm to generate offers based on prospect theory, social proof, and the anchoring effect. The input is the feature extraction results, and the output is the promotional offers.

[0399] Step 7:

[0400] The server collects data to recognize customer emotions in real time. It sends facial and voice data captured by the user through smart glasses to an emotion recognition engine such as Microsoft Azure Face API. The input is facial and voice data, and the output is the emotion recognition result.

[0401] Step 8:

[0402] The server customizes the proposal content based on the emotion recognition results. It generates optimistic proposals for customers who show positive emotions and proposals that address concerns for customers who show negative emotions. The inputs are the emotion recognition results and promotional proposals, and the output is the customized proposal content.

[0403] Step 9:

[0404] The server outputs the customized promotional offers to the display of the smart glasses, allowing the user to provide relevant offers to customers in real time. The input is the customized offer content, and the output is the offer displayed on the display of the smart glasses.

[0405] Step 10:

[0406] Based on the proposals provided by the server, users make presentations to retailers or their in-house marketing teams. The input is the proposal displayed on the smart glasses display, and the output is the actual sales promotion activity.

[0407] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0418] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0419] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0422] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0423] The present invention is a system that inputs market data, investor information, past sales promotion examples, etc., preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Specific embodiments for implementing the present invention will be described below.

[0424] 1. Data input:

[0425] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[0426] 2. Data preprocessing:

[0427] The server receives the input data and performs preprocessing, including cleaning the data, standardizing the format, filling in missing values, and normalizing the data, thereby ensuring the consistency and reliability of the data.

[0428] 3. Data analysis and feature extraction:

[0429] The server then analyzes the pre-processed dataset and extracts key features using techniques such as statistical analysis, clustering, and pattern detection, which can reveal, for example, the behavioral patterns and purchasing tendencies of specific consumer groups within a target market.

[0430] 4. Application of behavioral economics theory:

[0431] The server applies behavioral economics theory to the extracted features, specifically generating promotional offers based on prospect theory, social proof, anchoring effects, etc. These offers are intended to encourage consumer behavior and motivate purchases.

[0432] 5. Generate promotional offers:

[0433] The server generates specific sales promotion proposals based on the data analysis and behavioral economics theory. These proposals include what promotional methods should be used, the reasons for using them, and the expected effects. For example, they could propose a discount campaign for the first purchase of a new health food product, or an advertising message targeted at a specific target group.

[0434] 6. Proposal Development:

[0435] The user then makes a presentation to a retailer or an in-house marketing team based on the sales promotion proposals provided by the server. The proposals are well-grounded in theoretical background and concrete data, making them highly persuasive.

[0436] Example scenario

[0437] scenario:

[0438] A user is trying to bring a new health food product to market.

[0439] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[0440] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[0441] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[0442] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[0443] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[0444] The user then uses the proposals provided by the server to make detailed presentations to retail clients and internal marketing teams.

[0445] As described above, the present invention supports the formulation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] Users use terminals to input market data, investor relations information, past sales promotion cases, etc. Data formats include CSV files, Excel sheets, and database connections.

[0449] Step 2:

[0450] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[0451] Step 3:

[0452] The server handles data formatting, including standardizing date formats, normalizing numeric data, and tokenizing text data.

[0453] Step 4:

[0454] The server normalizes the data to ensure consistency across different data sets, for example by scaling each data set to a consistent value range.

[0455] Step 5:

[0456] The server analyzes the preprocessed data set, specifically calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[0457] Step 6:

[0458] The server performs clustering to classify consumer groups based on their characteristics, for example using the K-means algorithm to group similar consumers.

[0459] Step 7:

[0460] The server performs pattern detection and analyses for trends and correlations over time, including time series analysis and calculation of correlation matrices.

[0461] Step 8:

[0462] The server extracts important features, which includes generating new features, transforming existing features, and selecting important features based on feature importance.

[0463] Step 9:

[0464] The server applies behavioral economics theories to the extracted features to generate recommendations based on prospect theory, social proof, anchoring effect, etc.

[0465] Step 10:

[0466] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0467] Step 11:

[0468] The user receives the proposal provided by the server on the terminal and makes a presentation to the retailer or the company's internal marketing team.

[0469] Example 1

[0470] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0471] In conventional sales promotion systems, the processes of data input, preprocessing, analysis, and the generation of sales promotion proposals based on the analysis results were carried out independently, resulting in a lack of consistency and efficiency. Furthermore, it was difficult to automatically generate specific sales promotion proposals based on theories of behavioral economics, which required time and effort from the user. These issues made it difficult to develop a fast and effective sales promotion strategy.

[0472] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0473] In this invention, the server includes means for allowing a user to input market data, investor information, and past sales promotion examples using a terminal, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, and means for outputting the sales promotion proposals to the user. This makes it possible to perform the entire process from data input to the generation of sales promotion proposals as a single integrated process, enabling the formulation of a rapid and effective sales promotion strategy.

[0474] "User" refers to the person who operates the system and inputs information such as market data, investor information, and past promotional cases through a terminal.

[0475] "Terminal" refers to a device through which a user inputs data and which acts as an interface to the system.

[0476] "Market data" refers to basic information related to sales promotion, such as market trends, consumer behavior patterns, and economic indicators.

[0477] "Investor information" refers to a company's financial information, management strategy, performance forecasts, etc. provided to investors.

[0478] "Past sales promotion examples" refers to specific examples of sales promotion activities that have been implemented to date and their results.

[0479] "Server" refers to a central processing unit that pre-processes input data, performs data analysis, and generates promotional offers.

[0480] "Data preprocessing" refers to a series of processes to improve data quality, such as cleaning input data, standardizing formats, imputing missing values, and data normalization.

[0481] "Feature extraction" refers to the process of extracting important patterns and trends from pre-processed data.

[0482] "Behavioral economics" refers to theories that explain the psychological and social factors that influence human behavior and decision-making, such as prospect theory, social proof, and the anchoring effect.

[0483] "Sales promotion proposal" refers to a proposal that shows specific sales promotion methods and their effectiveness based on data analysis and behavioral economics theory.

[0484] "Output" refers to displaying the generated promotional offers to the user.

[0485] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Detailed embodiments of this system are described below.

[0486] Hardware and software used

[0487] Users use devices to input market data, investor relations information, and past sales promotions. Devices can be PCs, tablets, smartphones, etc. Input data can be in the form of CSV files, Excel sheets, or database connections.

[0488] The server preprocesses the received data, cleaning it, standardizing its format, imputing missing values, and normalizing it, using programming languages ​​such as Python and R and libraries such as Pandas and Numpy.

[0489] Based on the preprocessed dataset, the server performs data analysis such as statistical analysis, clustering, and pattern detection using machine learning libraries such as Scikit-learn and TensorFlow.

[0490] The server applies behavioral economics theories—specifically, prospect theory, social proof, and the anchoring effect—to generate promotional offers. The proposal generation incorporates NLP (natural language processing) techniques and leverages generative AI models, such as OpenAI's GPT-3 or BERT models.

[0491] Example scenario

[0492] scenario:

[0493] Consider a case where a user is trying to bring a new health food product to market.

[0494] 1. The user uses a terminal to input past sales data for health foods, examples of competitors' sales promotions, and consumer demographic information for the target market into the system. The input data is uploaded in Excel file format.

[0495] 2. The server receives the uploaded data and performs data cleaning. If an invalid data format is detected, it is recorded in an error log and corrected as much as possible. If missing values ​​are found, they are imputed using the mean or median.

[0496] 3. The server analyzes the preprocessed dataset and extracts important features. For example, a pattern may emerge: women in their 30s tend to prefer high-protein foods. Statistical analysis and clustering then clarify trends within the target customer group.

[0497] 4. The server applies behavioral economics theory to propose strategies using discount campaigns based on prospect theory and social proof citing competitor success stories. AI models are applied to automatically generate proposals.

[0498] 5. The server generates specific sales promotion proposals such as "discount campaigns for first-time purchases of health foods" or "advertising messages for specific target groups" and outputs them to the user.

[0499] Based on the sales promotion proposals provided by the server, users can make detailed presentations to retailers and in-house marketing teams. The proposals contain both theoretical background and concrete data-based justification, making them highly persuasive.

[0500] Prompt Sentence Examples

[0501] Example 1:

[0502] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[0503] Example 2:

[0504] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[0505] Generative AI model used

[0506] The system uses generative AI models such as OpenAI's GPT-3 and BERT to generate promotional offers, leveraging advanced natural language generation capabilities to provide users with effective and persuasive promotional strategies.

[0507] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0508] Step 1:

[0509] A user uses a terminal to input market data, investor relations information, and past sales promotion cases into the system. This input data is provided as a CSV file, Excel spreadsheet, etc. For example, a user selects an Excel file and clicks the upload button on the terminal to send the data to the system.

[0510] Input: Market data, investor relations information, and past promotions provided in the form of CSV files, Excel sheets, database connections, etc.

[0511] Output: Input data sent to the server

[0512] Step 2:

[0513] The server preprocesses the data received. Specifically, it performs processes such as data cleaning, format standardization, missing value imputation, and data normalization. If an invalid data format is detected, it records it in the error log and attempts to correct it if possible. If missing values ​​are found, they are imputed with the mean or median.

[0514] Input: Input data sent by the user

[0515] Output: Cleaned and uniformly formatted pre-processed data

[0516] Step 3:

[0517] The server analyzes the preprocessed data. Analysis methods include statistical analysis, clustering, and pattern detection. This reveals patterns of consumer behavior and market trends. For example, the server might extract a pattern that women in their 30s prefer high-protein foods.

[0518] Input: Preprocessed data

[0519] Output: Analysis results and important feature data

[0520] Step 4:

[0521] The server applies behavioral economics theory based on the analysis results. For example, it uses prospect theory, social proof, and the anchoring effect to generate effective sales promotion proposals. It utilizes generative AI models to automatically propose strategies to encourage consumer behavior.

[0522] Input: Analysis results and important feature data

[0523] Output: Sales promotion proposals based on the theory of behavioral economics

[0524] Step 5:

[0525] The server outputs the generated sales promotion proposal to the user. This proposal includes the promotional method to be used, the reasons for it, and the expected effects. The user then uses this proposal to make a presentation to a retailer or an internal marketing team. For example, the server might propose a "discount campaign for the first purchase of health foods" and simulate its effects.

[0526] Input: Sales promotion proposals based on the theory of behavioral economics

[0527] Output: Promotional offers provided to the user

[0528] Prompt Sentence Examples

[0529] Example 1:

[0530] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[0531] Example 2:

[0532] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[0533] (Application example 1)

[0534] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0535] While conventional sales promotion proposal systems are useful in generating proposals based on data analysis and behavioral economics theory, they lack a means to directly provide proposals based on consumer behavior and purchasing trends in real time. As a result, it is difficult to carry out immediate sales promotion activities in stores, and sales promotions cannot be carried out at the optimal time.

[0536] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0537] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals in real time, and means for outputting sales promotion proposals based on consumer behavior and purchasing trends in real time using a smart device. This makes it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[0538] "Market data" refers to information about market trends, competitive situations, consumer preferences and purchasing patterns, etc.

[0539] "Investor relations information" refers to information about a company's performance and strategies that is provided to investors.

[0540] "Past sales promotion cases" is information about the content and results of sales promotion activities carried out in the past.

[0541] "Data preprocessing" is the process of converting raw data into an analyzable form, including data cleaning, imputation of missing values, and normalization.

[0542] "Feature extraction" is the process of finding significant patterns and trends in a data set.

[0543] "Behavioral economics" is a science that analyzes economic behavior by taking into account psychological factors and is a theory that influences consumer decision-making.

[0544] "Prospect theory" is a theory that explains how people make decisions in risky situations.

[0545] "Social proof" is a psychological phenomenon in which people base their own behavior on the behavior of others.

[0546] The "anchoring effect" is a phenomenon in which the first information presented has a strong influence on subsequent decision-making.

[0547] "Real-time" means that processing is done instantly and results are obtained almost immediately.

[0548] "Sales promotion proposals" are specific methods and strategies for increasing consumer purchasing motivation.

[0549] A "smart device" is a device that has internet connectivity and can process and display a variety of information.

[0550] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. A detailed description of an embodiment of the present invention will be given below.

[0551] The system consists of the following stages:

[0552] 1. Data input

[0553] Users use terminals to input market data, investor relations information, and past promotions into the system, which is provided via CSV files, Excel sheets, or database connections.

[0554] 2. Data Preprocessing

[0555] The server receives the input data and performs preprocessing, which includes data cleaning, formatting standardization, missing value imputation, and data normalization. Specifically, data cleaning is performed using the Python Pandas library, and data normalization is performed using Scikit-learn.

[0556] 3. Data analysis and feature extraction

[0557] The server analyzes the pre-processed dataset and extracts key features using statistical analysis, clustering (e.g., K-means), and pattern detection. This process identifies behavioral patterns and purchasing trends among consumer groups.

[0558] 4. Application of behavioral economics theory

[0559] The server applies behavioral economics theory to the extracted features, specifically prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer behavior and increase purchasing intent.

[0560] 5. Generate promotional offers

[0561] The server generates specific sales promotion proposals based on the above data analysis and behavioral economics theory. These proposals are output in real time via smart devices (e.g., smart glasses). For example, if a store clerk is wearing smart glasses, appropriate sales promotion proposals will be instantly displayed based on the customer's behavioral patterns.

[0562] 6. Proposal Development

[0563] Users can carry out sales promotion activities in real time at the store based on sales promotion proposals provided by the server. In a specific example, a store clerk wearing smart glasses receives a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately provides that information to the customer.

[0564] Prompt Sentence Examples

[0565] "Generate real-time promotional offers using the following data:

[0566] Market Data

[0567] Investor information

[0568] Past promotional examples

[0569] The generated recommendations should be based on behavioral economics theory (e.g., prospect theory). They should demonstrate effectiveness for specific consumer groups and provide specific examples of sales strategies. The output should be in the following format:

[0570] {

[0571] "promotion_type": "discount",

[0572] "message": "Your 10% discount on our new protein bars is valid.",

[0573] "expected_effect": "Increased willingness to purchase"

[0574] }

[0575] "

[0576] As a result, the present invention systemizes a series of processes from data input to proposal creation and deployment, making it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[0577] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0578] Step 1:

[0579] Users use a terminal to input market data, investor relations information, and past promotions. Specifically, they upload the data to the system via a CSV file, Excel spreadsheet, or database connection. The input of this process is market data, investor relations information, and past promotions, and the output is that this data is stored on the server.

[0580] Step 2:

[0581] The server receives the input data and performs preprocessing. Specifically, it performs the following data processing: data cleaning, format standardization, missing value imputation, and data normalization. For example, it uses the Pandas library to impute missing values ​​and Scikit-learn to normalize the data. The input of this process is the input raw data, and the output is cleaned and normalized data.

[0582] Step 3:

[0583] The server analyzes the preprocessed data and extracts features. Specifically, it performs statistical analysis and clustering (e.g., K-means) to identify behavioral patterns and purchasing tendencies of consumer groups. For example, K-means clustering is used to identify target groups. The input of this process is the preprocessed data, and the output is consumer behavior patterns and features.

[0584] Step 4:

[0585] The server applies behavioral economics theory to the extracted features. Specifically, it generates recommendations using prospect theory, social proof, and the anchoring effect. For example, it uses prospect theory to recommend a "limited-time discount." The input to this process is the extracted feature data, and the output is a recommendation based on behavioral economics.

[0586] Step 5:

[0587] The server generates specific sales promotion proposals based on the theory of behavioral economics. The proposals include plans to be output in real time via smart devices (e.g., smart glasses). Specifically, the server outputs the generated sales promotion proposals in JSON format and sends them to the smart devices. The input of this process is the proposals based on behavioral economics, and the output is the real-time sales promotion proposals.

[0588] Step 6:

[0589] Based on the sales promotion proposals provided by the server, users can carry out sales promotion activities in real time at the store. For example, a sales clerk wearing smart glasses can receive a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately convey that information to the customer. The input to this process is the real-time sales promotion proposal sent from the server, and the output is the implementation of the sales promotion activity for the customer.

[0590] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0591] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments for implementing the present invention will be described below.

[0592] 1. Data input:

[0593] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[0594] 2. Data preprocessing:

[0595] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[0596] 3. Standardize data formats:

[0597] The server unifies the data format by unifying date formats, standardizing numeric data, tokenizing text data, etc.

[0598] 4. Data normalization:

[0599] The server normalizes the preprocessed data to ensure consistency across different datasets, for example by scaling each data set to a uniform value range.

[0600] 5. Data analysis and feature extraction:

[0601] The server analyzes the preprocessed dataset and performs basic statistical calculations, clustering, pattern detection, etc. to understand the basic characteristics of the data. It selects important features and reveals consumer behavior patterns and purchasing trends.

[0602] 6. Application of behavioral economics theory:

[0603] The server generates suggestions based on the extracted features, such as prospect theory, social proof, and anchoring effect, which can encourage consumer behavior and increase purchasing motivation.

[0604] 7. Incorporating an Emotion Engine:

[0605] The server recognizes the user's emotions using an emotion engine. The emotion engine detects the user's emotions using at least one of voice analysis, text analysis, and facial expression analysis. For example, the server collects real-time emotion data while the user is giving a presentation.

[0606] 8. Leveraging Emotional Data:

[0607] The server customizes the suggestions based on the user's emotional data, recognized by the emotion engine. If the user is expressing positive emotions, the server emphasizes optimistic suggestions. Conversely, if the user is expressing negative emotions, the server adds information to address concerns.

[0608] 9. Promotional Offer Generation:

[0609] The server generates specific promotional proposals based on the data analysis, application of behavioral economics theory, and sentiment data, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0610] 10. Proposal Development:

[0611] The user receives the proposals provided by the server on their device and makes presentations to retailers or their internal marketing teams. The proposals are customized based on emotional data, making them more persuasive to the target audience.

[0612] Example scenario

[0613] scenario:

[0614] A user is trying to bring a new health food product to market.

[0615] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[0616] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[0617] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[0618] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[0619] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[0620] The server uses an emotion engine to collect real-time emotional data from users during a presentation. For example, if a user has a positive reaction, the server can emphasize the content of the proposal in line with that emotion.

[0621] The user then uses the server-provided customized proposal to make detailed presentations to retailers and internal marketing teams.

[0622] As described above, the present invention supports the creation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals and by customizing them based on the user's emotions.

[0623] The processing flow will be explained below.

[0624] Step 1:

[0625] Users use terminals to input market data, investor relations information, and past promotional cases into the system, which can be provided in the form of CSV files, Excel spreadsheets, database connections, etc.

[0626] Step 2:

[0627] The server receives the input data and performs data cleaning, specifically by completing missing values, removing noise, and eliminating invalid data to improve the quality of the data.

[0628] Step 3:

[0629] The server handles data formatting, including standardizing date formats, standardizing numeric data, and tokenizing text data.

[0630] Step 4:

[0631] The server normalizes the data, scaling each data set to a consistent value range for consistency across different data sets.

[0632] Step 5:

[0633] The server analyzes the preprocessed dataset, calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[0634] Step 6:

[0635] The server performs clustering to classify consumer groups based on their characteristics, specifically by using the K-means algorithm to group similar consumers.

[0636] Step 7:

[0637] The server performs pattern detection, analyzing trends and correlations over time, and uncovering hidden patterns in the data through time series analysis and calculation of correlation matrices.

[0638] Step 8:

[0639] The server extracts important features, generates new features, transforms existing features, and selects the most important features using Feature Importance.

[0640] Step 9:

[0641] The server applies behavioral economics theories, such as prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer action.

[0642] Step 10:

[0643] The server recognizes the user's emotions using an emotion engine, which detects the user's emotions using voice analysis, text analysis, or facial expression analysis.

[0644] Step 11:

[0645] The server customizes the suggestions based on the user's emotional data. For example, if the user is expressing positive emotions, it will emphasize optimistic information, and if the user is expressing negative emotions, it will provide information that emphasizes safety and reliability.

[0646] Step 12:

[0647] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0648] Step 13:

[0649] The user receives the proposal information provided by the server on their device and makes a presentation to their retailer or in-house marketing team. The proposal information is customized based on emotional data, making it more persuasive to the target audience.

[0650] Example 2

[0651] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0652] Conventional sales promotion systems are limited to simple data analysis, and have limitations in predicting consumer behavior and generating effective proposals. Furthermore, proposals lack persuasiveness and effectiveness because they are not customized to take user emotions into account. To solve this problem, a system is needed that precisely analyzes input data, generates proposals based on theories of behavioral economics, and further customizes proposals by recognizing user emotions in real time.

[0653] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting market data, investor information, and past sales promotion cases and preprocessing the data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for recognizing user emotions and customizing the sales promotion proposals, and means for outputting the customized sales promotion proposals. This makes it possible to generate advanced and effective sales promotion proposals based on the input data and further customize the proposals according to the user's emotions.

[0654] "Market data" is information about market movements, trends, sales, consumer behavior, etc.

[0655] "Investor relations information" refers to information provided to investors, such as a company's financial situation, performance forecasts, and investment risks.

[0656] "Sales promotion cases" refers to information about the content, results, effects, etc. of sales promotion activities that have been carried out in the past.

[0657] "Data preprocessing" is the process of preparing input data for analysis by filling in missing values, removing noise, and excluding invalid data.

[0658] "Feature extraction" is a data analysis technique for finding useful patterns and trends in pre-processed data.

[0659] "Behavioral economics theory" is a theory that explains human psychology and behavior in economic activities, and includes prospect theory, social proof, and the anchoring effect.

[0660] A "sales promotion proposal" is a concrete presentation of strategies and ideas for promoting sales.

[0661] "Means for recognizing emotions" refers to technology that detects a user's emotions using voice analysis, text analysis, facial expression analysis, etc.

[0662] "Means for customizing suggestions" refers to technology that adjusts and adapts suggestions based on the user's emotional data.

[0663] "Data analysis" refers to techniques such as statistical analysis and clustering that are used to extract useful information from data.

[0664] "Statistical analysis" is a statistical method for understanding the distribution and trends of data.

[0665] "Clustering" is an analytical technique for classifying data into similar groups.

[0666] "Prospect theory" is a theory that explains how people evaluate gains and losses.

[0667] "Social proof" is a psychological phenomenon in which people base their decisions on the behavior and success stories of others.

[0668] The "anchoring effect" is a phenomenon in which initially presented information has a strong influence on subsequent decision-making.

[0669] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments of the present invention are described below.

[0670] 1. Data input

[0671] Users use a terminal to input market data, investor relations information, and past sales promotions into the system. Input data can be provided in the form of CSV files, Excel spreadsheets, or database connections, allowing users to easily utilize existing data resources to provide data to the system.

[0672] 2. Data Preprocessing

[0673] The server receives the input data and performs data cleaning using the Python Pandas library. Specifically, it imputes missing values, removes noise, and eliminates invalid data. This preprocessing step improves the quality of the data and increases the reliability of the subsequent analysis results.

[0674] 3. Standardization of data formats

[0675] The server standardizes the date format of the cleaned data to "YYYY-MM-DD" and uses Scikit-learn's scaling library to normalize numeric data. It also uses NLP tools to tokenize text data and convert it into a unified format, making the data consistent and easier to analyze.

[0676] 4. Data Normalization

[0677] The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1. This normalization step ensures consistency between different datasets, making them easier to compare.

[0678] 5. Data analysis and feature extraction

[0679] The server analyzes the preprocessed dataset, calculates basic statistics, and uses clustering algorithms (e.g., K-means clustering) to detect patterns and identify consumer behavior and purchasing trends. It then selects important features to help predict consumer behavior and develop marketing strategies.

[0680] 6. Application of behavioral economics theory

[0681] The server applies behavioral economics theories such as prospect theory, social proof, and anchoring effect to generate sales promotion proposals for the extracted features. For example, it is possible to stimulate consumer purchasing motivation by proposing a "limited-time discount promotion."

[0682] 7. Incorporating and utilizing an emotional engine

[0683] The server recognizes the user's emotions using an emotion engine. The emotion engine detects emotions in real time using voice analysis, text analysis, or facial expression analysis. The server customizes the suggestions based on the user's emotion data, emphasizing optimistic suggestions when the user shows positive emotions, and adding information to cover concerns when the user shows negative emotions.

[0684] 8. Promotional proposal generation and deployment

[0685] The server generates sales promotion proposals based on data analysis, behavioral economics theory, and emotional data. Specific examples include campaign design, advertising message creation, and product placement optimization. Users receive the proposals provided by the server on their devices and present them to clients or their internal marketing teams. Customized proposals based on emotional data can increase persuasiveness.

[0686] Example scenario

[0687] If a user is trying to bring a new health food product to market, the following prompt text could be used:

[0688] Example prompt sentence:

[0689] "Generate a sales promotion strategy for a high-protein food product targeted at women in their 30s. Using past sales data and competitor examples as a reference, create a proposal by applying prospect theory."

[0690] As described above, the present invention supports the development of more effective sales promotion strategies by systematizing a series of processes from data input to proposal creation and development, and by customizing based on the user's emotions.

[0691] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0692] Step 1:

[0693] Input: Users use terminals to upload market data, investor relations information, and past promotional cases into the system.

[0694] Specific operation: The user selects a CSV file or Excel sheet on the device and clicks the "Import" button.

[0695] Output: The server receives the input data and stores it in its internal database.

[0696] Step 2:

[0697] Input: The server retrieves the input data.

[0698] Specific operation: The server reads data from the database and performs data cleaning using Python's Pandas library.

[0699] Output: Cleaned data with missing values ​​imputed and noise and incorrect data removed.

[0700] Step 3:

[0701] Input: Cleaned data.

[0702] What it does: The server standardizes the date format to "YYYY-MM-DD", applies Scikit-learn's scaling library to normalize numeric data, and tokenizes text data using NLP tools.

[0703] Output: Uniformly formatted data.

[0704] Step 4:

[0705] Input: Uniformly formatted data.

[0706] What it does: The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1.

[0707] Output: Normalized data.

[0708] Step 5:

[0709] Input: Normalized data.

[0710] What it does: The server calculates basic statistics and uses the K-means clustering algorithm to find patterns in the data.

[0711] Output: Clustering results and feature extracted data.

[0712] Step 6:

[0713] Input: Feature extracted data.

[0714] What happens: The server applies prospect theory, social proof, and anchoring effects to generate promotional offers.

[0715] Output: Promotion proposal.

[0716] Step 7:

[0717] Input: Promotion offers and user interaction data.

[0718] How it works: The server uses an emotion engine to recognize the user's emotions in real time, using either voice analysis, text analysis, or facial expression analysis.

[0719] Output: User emotion data.

[0720] Step 8:

[0721] Input: Promotional offers and user sentiment data.

[0722] What happens: The server customizes promotional offers based on the user's emotions.

[0723] Output: A customized promotional offer.

[0724] Step 9:

[0725] Input: Customized promotional offer.

[0726] Specific operations: The server generates detailed specific proposals such as campaign design, advertising message creation, and product placement optimization.

[0727] Output: Final promotion proposal.

[0728] Step 10:

[0729] Input: Final promotion proposal.

[0730] Specific operation: The user receives the proposal from the server and uses the terminal to present it to clients or the internal marketing team.

[0731] Output: A customized promotional offer for presentation.

[0732] (Application example 2)

[0733] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0734] Conventional sales promotion systems were unable to analyze customer emotions and behavior in real time and make immediate proposals based on that analysis. This made it difficult to provide optimal sales strategies tailored to customer needs and emotions in a timely manner, limiting the effectiveness of sales promotions. In particular, in brick-and-mortar stores, it is necessary to quickly and accurately understand the emotions of each individual customer and make proposals based on that information, making it urgent to solve this problem.

[0735] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0736] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals, means for recognizing customer emotions in real time, and means for customizing the proposal content based on the recognized emotion data. This makes it possible to grasp customer emotions in real time in a physical store and instantly make optimal sales promotion proposals based on the customer emotions.

[0737] "Market data" refers to information such as market movements and trends, sales data, and consumer behavior.

[0738] "Investor information" refers to information necessary for investors to make decisions, such as stock prices, investment risks, and corporate performance.

[0739] "Past sales promotion examples" refers to information about the implementation and effectiveness of past promotions and campaigns.

[0740] "Preprocessing" refers to tasks such as data cleaning, filling in missing values, and standardizing formats to convert input data into a format that is easy to analyze.

[0741] "Feature extraction" refers to the process of finding important patterns and trends from preprocessed data that are useful for data analysis and machine learning.

[0742] "Behavioral economics" refers to a field of study that combines psychology and economics to study the decision-making motivations and behavior of consumers and investors.

[0743] Prospect theory is a theory that explains why consumers behave differently depending on whether they are gaining or losing something, and is based on differences in the evaluation of risks and benefits.

[0744] "Social proof" is a theory that explains consumer psychology, in which people base their own behavior on the behavior of others.

[0745] The "anchoring effect" is a theory that explains people's tendency to base subsequent judgments on the information they first receive.

[0746] "Emotion recognition" refers to technology that identifies a user's emotions in real time through voice analysis, text analysis, facial expression analysis, etc.

[0747] "Sales promotion proposals" refer to proposals that scientifically derive promotional campaigns and advertising messages for specific products or services in order to carry out marketing activities effectively.

[0748] In order to implement the present invention, the following system must be constructed.

[0749] First, the server has a means of receiving input market data, investor relations information, and past sales promotion cases. This means can import data in a variety of formats, such as CSV files, Excel sheets, and database connections, making it easy for users to input the data they need.

[0750] The server then has the means to preprocess the input data, cleaning it, imputing missing values, removing noise, filtering out invalid data, etc. This process can be automated using Python scripts.

[0751] Furthermore, statistical analysis, clustering, and pattern detection are performed to extract features from the preprocessed data. This allows us to understand the basic features of the data and reveal consumer behavior patterns and purchasing trends. The tools used are Python libraries (e.g., Pandas, Scikit-learn).

[0752] The system applies behavioral economics theory, such as prospect theory, social proof, and the anchoring effect, to generate sales promotion proposals based on data analysis results. This proposal generation can be achieved using an algorithm built in Python.

[0753] The invention also incorporates a means for recognizing users' emotions in real time. This involves using a camera and microphone in the smart glasses to capture the customer's facial expressions and voice, and then analyzing the data with an emotion recognition engine such as Microsoft Azure Face API. Based on the emotional data recognized at this stage, the system can customize the recommendations.

[0754] The results of this data processing and analysis are displayed on the smart glasses' display in real time, enabling prompt sales promotion proposals. Finally, the proposals output from the system can be used by users when making presentations to retailers or their internal marketing teams.

[0755] Examples:

[0756] For example, when a salesperson at a shoe store puts on smart glasses and starts serving customers, the following flow is assumed.

[0757] 1. A store clerk puts on the smart glasses and begins interacting with the customer.

[0758] 2. The smart glasses capture the customer's facial expressions and voice, and the data is sent to the server.

[0759] 3. Emotion recognition is performed in real time on the server, and the results are sent back to the smart glasses.

[0760] 4. Based on past data and behavioral economics theory, the server will suggest "new sports shoes" to customers who show positive emotions.

[0761] 5. The suggestions are displayed on the smart glasses' display, and the store clerk uses them to suggest appropriate products.

[0762] Prompt Sentence Examples

[0763] Customer sentiment analysis results: Positive

[0764] Past data analysis results: New sports shoes are effective for customers who show positive emotions

[0765] Suggestion: Recommend new sports shoes

[0766] This makes it possible for brick-and-mortar stores to instantly make optimal sales promotion proposals that reflect the customer's emotions.

[0767] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0768] Step 1:

[0769] The server receives market data, investor relations information, and past promotional examples from users in the form of CSV files, Excel spreadsheets, or database connections. The server loads this data into memory and creates an input dataset.

[0770] Step 2:

[0771] The server preprocesses the input data. This process includes data cleaning (filling in missing values, removing noise, and eliminating invalid data). Specifically, the dataset is prepared using a Python script. The input is the input data, and the output is the cleaned dataset.

[0772] Step 3:

[0773] The server converts the cleaned data into a unified format, which includes unifying date formats, normalizing numeric data, and tokenizing text data. The input is the cleaned dataset, and the output is the unified dataset.

[0774] Step 4:

[0775] The server analyzes the unified data set, calculates basic statistics, performs clustering, and detects patterns. Specifically, it performs data analysis using Python's Pandas and Scikit-learn. The input is the unified data set, and the output is the analysis results.

[0776] Step 5:

[0777] The server extracts features based on the results of data analysis. It selects important features to clarify consumer behavior patterns and purchasing trends. The input is the analysis results, and the output is the feature extraction results.

[0778] Step 6:

[0779] The server applies behavioral economics theory to the feature extraction results to generate promotional offers. Specifically, it uses an algorithm to generate offers based on prospect theory, social proof, and the anchoring effect. The input is the feature extraction results, and the output is the promotional offers.

[0780] Step 7:

[0781] The server collects data to recognize customer emotions in real time. It sends facial and voice data captured by the user through smart glasses to an emotion recognition engine such as Microsoft Azure Face API. The input is facial and voice data, and the output is the emotion recognition result.

[0782] Step 8:

[0783] The server customizes the proposal content based on the emotion recognition results. It generates optimistic proposals for customers who show positive emotions and proposals that address concerns for customers who show negative emotions. The inputs are the emotion recognition results and promotional proposals, and the output is the customized proposal content.

[0784] Step 9:

[0785] The server outputs the customized promotional offers to the display of the smart glasses, allowing the user to provide relevant offers to customers in real time. The input is the customized offer content, and the output is the offer displayed on the display of the smart glasses.

[0786] Step 10:

[0787] Based on the proposals provided by the server, users make presentations to retailers or their in-house marketing teams. The input is the proposal displayed on the smart glasses display, and the output is the actual sales promotion activity.

[0788] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0789] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0790] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0791] [Third embodiment]

[0792] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0793] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0794] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0795] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0796] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0797] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0798] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0799] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0800] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0801] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0802] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0803] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0804] The present invention is a system that inputs market data, investor information, past sales promotion examples, etc., preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Specific embodiments for implementing the present invention will be described below.

[0805] 1. Data input:

[0806] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[0807] 2. Data preprocessing:

[0808] The server receives the input data and performs preprocessing, including cleaning the data, standardizing the format, filling in missing values, and normalizing the data, thereby ensuring the consistency and reliability of the data.

[0809] 3. Data analysis and feature extraction:

[0810] The server then analyzes the pre-processed dataset and extracts key features using techniques such as statistical analysis, clustering, and pattern detection, which can reveal, for example, the behavioral patterns and purchasing tendencies of specific consumer groups within a target market.

[0811] 4. Application of behavioral economics theory:

[0812] The server applies behavioral economics theory to the extracted features, specifically generating promotional offers based on prospect theory, social proof, anchoring effects, etc. These offers are intended to encourage consumer behavior and motivate purchases.

[0813] 5. Generate promotional offers:

[0814] The server generates specific sales promotion proposals based on the data analysis and behavioral economics theory. These proposals include what promotional methods should be used, the reasons for using them, and the expected effects. For example, they could propose a discount campaign for the first purchase of a new health food product, or an advertising message targeted at a specific target group.

[0815] 6. Proposal Development:

[0816] The user then makes a presentation to a retailer or an in-house marketing team based on the sales promotion proposals provided by the server. The proposals are well-grounded in theoretical background and concrete data, making them highly persuasive.

[0817] Example scenario

[0818] scenario:

[0819] A user is trying to bring a new health food product to market.

[0820] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[0821] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[0822] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[0823] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[0824] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[0825] The user then uses the proposals provided by the server to make detailed presentations to retail clients and internal marketing teams.

[0826] As described above, the present invention supports the formulation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals.

[0827] The processing flow will be explained below.

[0828] Step 1:

[0829] Users use terminals to input market data, investor relations information, past sales promotion cases, etc. Data formats include CSV files, Excel sheets, and database connections.

[0830] Step 2:

[0831] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[0832] Step 3:

[0833] The server handles data formatting, including standardizing date formats, normalizing numeric data, and tokenizing text data.

[0834] Step 4:

[0835] The server normalizes the data to ensure consistency across different data sets, for example by scaling each data set to a consistent value range.

[0836] Step 5:

[0837] The server analyzes the preprocessed data set, specifically calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[0838] Step 6:

[0839] The server performs clustering to classify consumer groups based on their characteristics, for example using the K-means algorithm to group similar consumers.

[0840] Step 7:

[0841] The server performs pattern detection and analyses for trends and correlations over time, including time series analysis and calculation of correlation matrices.

[0842] Step 8:

[0843] The server extracts important features, which includes generating new features, transforming existing features, and selecting important features based on feature importance.

[0844] Step 9:

[0845] The server applies behavioral economics theories to the extracted features to generate recommendations based on prospect theory, social proof, anchoring effect, etc.

[0846] Step 10:

[0847] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0848] Step 11:

[0849] The user receives the proposal provided by the server on the terminal and makes a presentation to the retailer or the company's internal marketing team.

[0850] Example 1

[0851] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0852] In conventional sales promotion systems, the processes of data input, preprocessing, analysis, and the generation of sales promotion proposals based on the analysis results were carried out independently, resulting in a lack of consistency and efficiency. Furthermore, it was difficult to automatically generate specific sales promotion proposals based on theories of behavioral economics, which required time and effort from the user. These issues made it difficult to develop a fast and effective sales promotion strategy.

[0853] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0854] In this invention, the server includes means for allowing a user to input market data, investor information, and past sales promotion examples using a terminal, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, and means for outputting the sales promotion proposals to the user. This makes it possible to perform the entire process from data input to the generation of sales promotion proposals as a single integrated process, enabling the formulation of a rapid and effective sales promotion strategy.

[0855] "User" refers to the person who operates the system and inputs information such as market data, investor information, and past promotional cases through a terminal.

[0856] "Terminal" refers to a device through which a user inputs data and which acts as an interface to the system.

[0857] "Market data" refers to basic information related to sales promotion, such as market trends, consumer behavior patterns, and economic indicators.

[0858] "Investor information" refers to a company's financial information, management strategy, performance forecasts, etc. provided to investors.

[0859] "Past sales promotion examples" refers to specific examples of sales promotion activities that have been implemented to date and their results.

[0860] "Server" refers to a central processing unit that pre-processes input data, performs data analysis, and generates promotional offers.

[0861] "Data preprocessing" refers to a series of processes to improve data quality, such as cleaning input data, standardizing formats, imputing missing values, and data normalization.

[0862] "Feature extraction" refers to the process of extracting important patterns and trends from pre-processed data.

[0863] "Behavioral economics" refers to theories that explain the psychological and social factors that influence human behavior and decision-making, such as prospect theory, social proof, and the anchoring effect.

[0864] "Sales promotion proposal" refers to a proposal that shows specific sales promotion methods and their effectiveness based on data analysis and behavioral economics theory.

[0865] "Output" refers to displaying the generated promotional offers to the user.

[0866] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Detailed embodiments of this system are described below.

[0867] Hardware and software used

[0868] Users use devices to input market data, investor relations information, and past sales promotions. Devices can be PCs, tablets, smartphones, etc. Input data can be in the form of CSV files, Excel sheets, or database connections.

[0869] The server preprocesses the received data, cleaning it, standardizing its format, imputing missing values, and normalizing it, using programming languages ​​such as Python and R and libraries such as Pandas and Numpy.

[0870] Based on the preprocessed dataset, the server performs data analysis such as statistical analysis, clustering, and pattern detection using machine learning libraries such as Scikit-learn and TensorFlow.

[0871] The server applies behavioral economics theories—specifically, prospect theory, social proof, and the anchoring effect—to generate promotional offers. The proposal generation incorporates NLP (natural language processing) techniques and leverages generative AI models, such as OpenAI's GPT-3 or BERT models.

[0872] Example scenario

[0873] scenario:

[0874] Consider a case where a user is trying to bring a new health food product to market.

[0875] 1. The user uses a terminal to input past sales data for health foods, examples of competitors' sales promotions, and consumer demographic information for the target market into the system. The input data is uploaded in Excel file format.

[0876] 2. The server receives the uploaded data and performs data cleaning. If an invalid data format is detected, it is recorded in an error log and corrected as much as possible. If missing values ​​are found, they are imputed using the mean or median.

[0877] 3. The server analyzes the preprocessed dataset and extracts important features. For example, a pattern may emerge: women in their 30s tend to prefer high-protein foods. Statistical analysis and clustering then clarify trends within the target customer group.

[0878] 4. The server applies behavioral economics theory to propose strategies using discount campaigns based on prospect theory and social proof citing competitor success stories. AI models are applied to automatically generate proposals.

[0879] 5. The server generates specific sales promotion proposals such as "discount campaigns for first-time purchases of health foods" or "advertising messages for specific target groups" and outputs them to the user.

[0880] Based on the sales promotion proposals provided by the server, users can make detailed presentations to retailers and in-house marketing teams. The proposals contain both theoretical background and concrete data-based justification, making them highly persuasive.

[0881] Prompt Sentence Examples

[0882] Example 1:

[0883] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[0884] Example 2:

[0885] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[0886] Generative AI model used

[0887] The system uses generative AI models such as OpenAI's GPT-3 and BERT to generate promotional offers, leveraging advanced natural language generation capabilities to provide users with effective and persuasive promotional strategies.

[0888] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0889] Step 1:

[0890] A user uses a terminal to input market data, investor relations information, and past sales promotion cases into the system. This input data is provided as a CSV file, Excel spreadsheet, etc. For example, a user selects an Excel file and clicks the upload button on the terminal to send the data to the system.

[0891] Input: Market data, investor relations information, and past promotions provided in the form of CSV files, Excel sheets, database connections, etc.

[0892] Output: Input data sent to the server

[0893] Step 2:

[0894] The server preprocesses the data received. Specifically, it performs processes such as data cleaning, format standardization, missing value imputation, and data normalization. If an invalid data format is detected, it records it in the error log and attempts to correct it if possible. If missing values ​​are found, they are imputed with the mean or median.

[0895] Input: Input data sent by the user

[0896] Output: Cleaned and uniformly formatted pre-processed data

[0897] Step 3:

[0898] The server analyzes the preprocessed data. Analysis methods include statistical analysis, clustering, and pattern detection. This reveals patterns of consumer behavior and market trends. For example, the server might extract a pattern that women in their 30s prefer high-protein foods.

[0899] Input: Preprocessed data

[0900] Output: Analysis results and important feature data

[0901] Step 4:

[0902] The server applies behavioral economics theory based on the analysis results. For example, it uses prospect theory, social proof, and the anchoring effect to generate effective sales promotion proposals. It utilizes generative AI models to automatically propose strategies to encourage consumer behavior.

[0903] Input: Analysis results and important feature data

[0904] Output: Sales promotion proposals based on the theory of behavioral economics

[0905] Step 5:

[0906] The server outputs the generated sales promotion proposal to the user. This proposal includes the promotional method to be used, the reasons for it, and the expected effects. The user then uses this proposal to make a presentation to a retailer or an internal marketing team. For example, the server might propose a "discount campaign for the first purchase of health foods" and simulate its effects.

[0907] Input: Sales promotion proposals based on the theory of behavioral economics

[0908] Output: Promotional offers provided to the user

[0909] Prompt Sentence Examples

[0910] Example 1:

[0911] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[0912] Example 2:

[0913] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[0914] (Application example 1)

[0915] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0916] While conventional sales promotion proposal systems are useful in generating proposals based on data analysis and behavioral economics theory, they lack a means to directly provide proposals based on consumer behavior and purchasing trends in real time. As a result, it is difficult to carry out immediate sales promotion activities in stores, and sales promotions cannot be carried out at the optimal time.

[0917] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0918] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals in real time, and means for outputting sales promotion proposals based on consumer behavior and purchasing trends in real time using a smart device. This makes it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[0919] "Market data" refers to information about market trends, competitive situations, consumer preferences and purchasing patterns, etc.

[0920] "Investor relations information" refers to information about a company's performance and strategies that is provided to investors.

[0921] "Past sales promotion cases" is information about the content and results of sales promotion activities carried out in the past.

[0922] "Data preprocessing" is the process of converting raw data into an analyzable form, including data cleaning, imputation of missing values, and normalization.

[0923] "Feature extraction" is the process of finding significant patterns and trends in a data set.

[0924] "Behavioral economics" is a science that analyzes economic behavior by taking into account psychological factors and is a theory that influences consumer decision-making.

[0925] "Prospect theory" is a theory that explains how people make decisions in risky situations.

[0926] "Social proof" is a psychological phenomenon in which people base their own behavior on the behavior of others.

[0927] The "anchoring effect" is a phenomenon in which the first information presented has a strong influence on subsequent decision-making.

[0928] "Real-time" means that processing is done instantly and results are obtained almost immediately.

[0929] "Sales promotion proposals" are specific methods and strategies for increasing consumer purchasing motivation.

[0930] A "smart device" is a device that has internet connectivity and can process and display a variety of information.

[0931] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. A detailed description of an embodiment of the present invention will be given below.

[0932] The system consists of the following stages:

[0933] 1. Data input

[0934] Users use terminals to input market data, investor relations information, and past promotions into the system, which is provided via CSV files, Excel sheets, or database connections.

[0935] 2. Data Preprocessing

[0936] The server receives the input data and performs preprocessing, which includes data cleaning, formatting standardization, missing value imputation, and data normalization. Specifically, data cleaning is performed using the Python Pandas library, and data normalization is performed using Scikit-learn.

[0937] 3. Data analysis and feature extraction

[0938] The server analyzes the pre-processed dataset and extracts key features using statistical analysis, clustering (e.g., K-means), and pattern detection. This process identifies behavioral patterns and purchasing trends among consumer groups.

[0939] 4. Application of behavioral economics theory

[0940] The server applies behavioral economics theory to the extracted features, specifically prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer behavior and increase purchasing intent.

[0941] 5. Generate promotional offers

[0942] The server generates specific sales promotion proposals based on the above data analysis and behavioral economics theory. These proposals are output in real time via smart devices (e.g., smart glasses). For example, if a store clerk is wearing smart glasses, appropriate sales promotion proposals will be instantly displayed based on the customer's behavioral patterns.

[0943] 6. Proposal Development

[0944] Users can carry out sales promotion activities in real time at the store based on sales promotion proposals provided by the server. In a specific example, a store clerk wearing smart glasses receives a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately provides that information to the customer.

[0945] Prompt Sentence Examples

[0946] "Generate real-time promotional offers using the following data:

[0947] Market Data

[0948] Investor information

[0949] Past promotional examples

[0950] The generated recommendations should be based on behavioral economics theory (e.g., prospect theory). They should demonstrate effectiveness for specific consumer groups and provide specific examples of sales strategies. The output should be in the following format:

[0951] {

[0952] "promotion_type": "discount",

[0953] "message": "Your 10% discount on our new protein bars is valid.",

[0954] "expected_effect": "Increased willingness to purchase"

[0955] }

[0956] "

[0957] As a result, the present invention systemizes a series of processes from data input to proposal creation and deployment, making it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[0958] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0959] Step 1:

[0960] Users use a terminal to input market data, investor relations information, and past promotions. Specifically, they upload the data to the system via a CSV file, Excel spreadsheet, or database connection. The input of this process is market data, investor relations information, and past promotions, and the output is that this data is stored on the server.

[0961] Step 2:

[0962] The server receives the input data and performs preprocessing. Specifically, it performs the following data processing: data cleaning, format standardization, missing value imputation, and data normalization. For example, it uses the Pandas library to impute missing values ​​and Scikit-learn to normalize the data. The input of this process is the input raw data, and the output is cleaned and normalized data.

[0963] Step 3:

[0964] The server analyzes the preprocessed data and extracts features. Specifically, it performs statistical analysis and clustering (e.g., K-means) to identify behavioral patterns and purchasing tendencies of consumer groups. For example, K-means clustering is used to identify target groups. The input of this process is the preprocessed data, and the output is consumer behavior patterns and features.

[0965] Step 4:

[0966] The server applies behavioral economics theory to the extracted features. Specifically, it generates recommendations using prospect theory, social proof, and the anchoring effect. For example, it uses prospect theory to recommend a "limited-time discount." The input to this process is the extracted feature data, and the output is a recommendation based on behavioral economics.

[0967] Step 5:

[0968] The server generates specific sales promotion proposals based on the theory of behavioral economics. The proposals include plans to be output in real time via smart devices (e.g., smart glasses). Specifically, the server outputs the generated sales promotion proposals in JSON format and sends them to the smart devices. The input of this process is the proposals based on behavioral economics, and the output is the real-time sales promotion proposals.

[0969] Step 6:

[0970] Based on the sales promotion proposals provided by the server, users can carry out sales promotion activities in real time at the store. For example, a sales clerk wearing smart glasses can receive a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately convey that information to the customer. The input to this process is the real-time sales promotion proposal sent from the server, and the output is the implementation of the sales promotion activity for the customer.

[0971] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0972] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments for implementing the present invention will be described below.

[0973] 1. Data input:

[0974] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[0975] 2. Data preprocessing:

[0976] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[0977] 3. Standardize data formats:

[0978] The server unifies the data format by unifying date formats, standardizing numeric data, tokenizing text data, etc.

[0979] 4. Data normalization:

[0980] The server normalizes the preprocessed data to ensure consistency across different datasets, for example by scaling each data set to a uniform value range.

[0981] 5. Data analysis and feature extraction:

[0982] The server analyzes the preprocessed dataset and performs basic statistical calculations, clustering, pattern detection, etc. to understand the basic characteristics of the data. It selects important features and reveals consumer behavior patterns and purchasing trends.

[0983] 6. Application of behavioral economics theory:

[0984] The server generates suggestions based on the extracted features, such as prospect theory, social proof, and anchoring effect, which can encourage consumer behavior and increase purchasing motivation.

[0985] 7. Incorporating an Emotion Engine:

[0986] The server recognizes the user's emotions using an emotion engine. The emotion engine detects the user's emotions using at least one of voice analysis, text analysis, and facial expression analysis. For example, the server collects real-time emotion data while the user is giving a presentation.

[0987] 8. Leveraging Emotional Data:

[0988] The server customizes the suggestions based on the user's emotional data, recognized by the emotion engine. If the user is expressing positive emotions, the server emphasizes optimistic suggestions. Conversely, if the user is expressing negative emotions, the server adds information to address concerns.

[0989] 9. Promotional Offer Generation:

[0990] The server generates specific promotional proposals based on the data analysis, application of behavioral economics theory, and sentiment data, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[0991] 10. Proposal Development:

[0992] The user receives the proposals provided by the server on their device and makes presentations to retailers or their internal marketing teams. The proposals are customized based on emotional data, making them more persuasive to the target audience.

[0993] Example scenario

[0994] scenario:

[0995] A user is trying to bring a new health food product to market.

[0996] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[0997] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[0998] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[0999] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[1000] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[1001] The server uses an emotion engine to collect real-time emotional data from users during a presentation. For example, if a user has a positive reaction, the server can emphasize the content of the proposal in line with that emotion.

[1002] The user then uses the server-provided customized proposal to make detailed presentations to retailers and internal marketing teams.

[1003] As described above, the present invention supports the creation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals and by customizing them based on the user's emotions.

[1004] The processing flow will be explained below.

[1005] Step 1:

[1006] Users use terminals to input market data, investor relations information, and past promotional cases into the system, which can be provided in the form of CSV files, Excel spreadsheets, database connections, etc.

[1007] Step 2:

[1008] The server receives the input data and performs data cleaning, specifically by completing missing values, removing noise, and eliminating invalid data to improve the quality of the data.

[1009] Step 3:

[1010] The server handles data formatting, including standardizing date formats, standardizing numeric data, and tokenizing text data.

[1011] Step 4:

[1012] The server normalizes the data, scaling each data set to a consistent value range for consistency across different data sets.

[1013] Step 5:

[1014] The server analyzes the preprocessed dataset, calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[1015] Step 6:

[1016] The server performs clustering to classify consumer groups based on their characteristics, specifically by using the K-means algorithm to group similar consumers.

[1017] Step 7:

[1018] The server performs pattern detection, analyzing trends and correlations over time, and uncovering hidden patterns in the data through time series analysis and calculation of correlation matrices.

[1019] Step 8:

[1020] The server extracts important features, generates new features, transforms existing features, and selects the most important features using Feature Importance.

[1021] Step 9:

[1022] The server applies behavioral economics theories, such as prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer action.

[1023] Step 10:

[1024] The server recognizes the user's emotions using an emotion engine, which detects the user's emotions using voice analysis, text analysis, or facial expression analysis.

[1025] Step 11:

[1026] The server customizes the suggestions based on the user's emotional data. For example, if the user is expressing positive emotions, it will emphasize optimistic information, and if the user is expressing negative emotions, it will provide information that emphasizes safety and reliability.

[1027] Step 12:

[1028] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[1029] Step 13:

[1030] The user receives the proposal information provided by the server on their device and makes a presentation to their retailer or in-house marketing team. The proposal information is customized based on emotional data, making it more persuasive to the target audience.

[1031] Example 2

[1032] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1033] Conventional sales promotion systems are limited to simple data analysis, and have limitations in predicting consumer behavior and generating effective proposals. Furthermore, proposals lack persuasiveness and effectiveness because they are not customized to take user emotions into account. To solve this problem, a system is needed that precisely analyzes input data, generates proposals based on theories of behavioral economics, and further customizes proposals by recognizing user emotions in real time.

[1034] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting market data, investor information, and past sales promotion cases and preprocessing the data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for recognizing user emotions and customizing the sales promotion proposals, and means for outputting the customized sales promotion proposals. This makes it possible to generate advanced and effective sales promotion proposals based on the input data and further customize the proposals according to the user's emotions.

[1035] "Market data" is information about market movements, trends, sales, consumer behavior, etc.

[1036] "Investor relations information" refers to information provided to investors, such as a company's financial situation, performance forecasts, and investment risks.

[1037] "Sales promotion cases" refers to information about the content, results, effects, etc. of sales promotion activities that have been carried out in the past.

[1038] "Data preprocessing" is the process of preparing input data for analysis by filling in missing values, removing noise, and excluding invalid data.

[1039] "Feature extraction" is a data analysis technique for finding useful patterns and trends in pre-processed data.

[1040] "Behavioral economics theory" is a theory that explains human psychology and behavior in economic activities, and includes prospect theory, social proof, and the anchoring effect.

[1041] A "sales promotion proposal" is a concrete presentation of strategies and ideas for promoting sales.

[1042] "Means for recognizing emotions" refers to technology that detects a user's emotions using voice analysis, text analysis, facial expression analysis, etc.

[1043] "Means for customizing suggestions" refers to technology that adjusts and adapts suggestions based on the user's emotional data.

[1044] "Data analysis" refers to techniques such as statistical analysis and clustering that are used to extract useful information from data.

[1045] "Statistical analysis" is a statistical method for understanding the distribution and trends of data.

[1046] "Clustering" is an analytical technique for classifying data into similar groups.

[1047] "Prospect theory" is a theory that explains how people evaluate gains and losses.

[1048] "Social proof" is a psychological phenomenon in which people base their decisions on the behavior and success stories of others.

[1049] The "anchoring effect" is a phenomenon in which initially presented information has a strong influence on subsequent decision-making.

[1050] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments of the present invention are described below.

[1051] 1. Data input

[1052] Users use a terminal to input market data, investor relations information, and past sales promotions into the system. Input data can be provided in the form of CSV files, Excel spreadsheets, or database connections, allowing users to easily utilize existing data resources to provide data to the system.

[1053] 2. Data Preprocessing

[1054] The server receives the input data and performs data cleaning using the Python Pandas library. Specifically, it imputes missing values, removes noise, and eliminates invalid data. This preprocessing step improves the quality of the data and increases the reliability of the subsequent analysis results.

[1055] 3. Standardization of data formats

[1056] The server standardizes the date format of the cleaned data to "YYYY-MM-DD" and uses Scikit-learn's scaling library to normalize numeric data. It also uses NLP tools to tokenize text data and convert it into a unified format, making the data consistent and easier to analyze.

[1057] 4. Data Normalization

[1058] The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1. This normalization step ensures consistency between different datasets, making them easier to compare.

[1059] 5. Data analysis and feature extraction

[1060] The server analyzes the preprocessed dataset, calculates basic statistics, and uses clustering algorithms (e.g., K-means clustering) to detect patterns and identify consumer behavior and purchasing trends. It then selects important features to help predict consumer behavior and develop marketing strategies.

[1061] 6. Application of behavioral economics theory

[1062] The server applies behavioral economics theories such as prospect theory, social proof, and anchoring effect to generate sales promotion proposals for the extracted features. For example, it is possible to stimulate consumer purchasing motivation by proposing a "limited-time discount promotion."

[1063] 7. Incorporating and utilizing an emotional engine

[1064] The server recognizes the user's emotions using an emotion engine. The emotion engine detects emotions in real time using voice analysis, text analysis, or facial expression analysis. The server customizes the suggestions based on the user's emotion data, emphasizing optimistic suggestions when the user shows positive emotions, and adding information to cover concerns when the user shows negative emotions.

[1065] 8. Promotional proposal generation and deployment

[1066] The server generates sales promotion proposals based on data analysis, behavioral economics theory, and emotional data. Specific examples include campaign design, advertising message creation, and product placement optimization. Users receive the proposals provided by the server on their devices and present them to clients or their internal marketing teams. Customized proposals based on emotional data can increase persuasiveness.

[1067] Example scenario

[1068] If a user is trying to bring a new health food product to market, the following prompt text could be used:

[1069] Example prompt sentence:

[1070] "Generate a sales promotion strategy for a high-protein food product targeted at women in their 30s. Using past sales data and competitor examples as a reference, create a proposal by applying prospect theory."

[1071] As described above, the present invention supports the development of more effective sales promotion strategies by systematizing a series of processes from data input to proposal creation and development, and by customizing based on the user's emotions.

[1072] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1073] Step 1:

[1074] Input: Users use terminals to upload market data, investor relations information, and past promotional cases into the system.

[1075] Specific operation: The user selects a CSV file or Excel sheet on the device and clicks the "Import" button.

[1076] Output: The server receives the input data and stores it in its internal database.

[1077] Step 2:

[1078] Input: The server retrieves the input data.

[1079] Specific operation: The server reads data from the database and performs data cleaning using Python's Pandas library.

[1080] Output: Cleaned data with missing values ​​imputed and noise and incorrect data removed.

[1081] Step 3:

[1082] Input: Cleaned data.

[1083] What it does: The server standardizes the date format to "YYYY-MM-DD", applies Scikit-learn's scaling library to normalize numeric data, and tokenizes text data using NLP tools.

[1084] Output: Uniformly formatted data.

[1085] Step 4:

[1086] Input: Uniformly formatted data.

[1087] What it does: The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1.

[1088] Output: Normalized data.

[1089] Step 5:

[1090] Input: Normalized data.

[1091] What it does: The server calculates basic statistics and uses the K-means clustering algorithm to find patterns in the data.

[1092] Output: Clustering results and feature extracted data.

[1093] Step 6:

[1094] Input: Feature extracted data.

[1095] What happens: The server applies prospect theory, social proof, and anchoring effects to generate promotional offers.

[1096] Output: Promotion proposal.

[1097] Step 7:

[1098] Input: Promotion offers and user interaction data.

[1099] How it works: The server uses an emotion engine to recognize the user's emotions in real time, using either voice analysis, text analysis, or facial expression analysis.

[1100] Output: User emotion data.

[1101] Step 8:

[1102] Input: Promotional offers and user sentiment data.

[1103] What happens: The server customizes promotional offers based on the user's emotions.

[1104] Output: A customized promotional offer.

[1105] Step 9:

[1106] Input: Customized promotional offer.

[1107] Specific operations: The server generates detailed specific proposals such as campaign design, advertising message creation, and product placement optimization.

[1108] Output: Final promotion proposal.

[1109] Step 10:

[1110] Input: Final promotion proposal.

[1111] Specific operation: The user receives the proposal from the server and uses the terminal to present it to clients or the internal marketing team.

[1112] Output: A customized promotional offer for presentation.

[1113] (Application example 2)

[1114] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1115] Conventional sales promotion systems were unable to analyze customer emotions and behavior in real time and make immediate proposals based on that analysis. This made it difficult to provide optimal sales strategies tailored to customer needs and emotions in a timely manner, limiting the effectiveness of sales promotions. In particular, in brick-and-mortar stores, it is necessary to quickly and accurately understand the emotions of each individual customer and make proposals based on that information, making it urgent to solve this problem.

[1116] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1117] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals, means for recognizing customer emotions in real time, and means for customizing the proposal content based on the recognized emotion data. This makes it possible to grasp customer emotions in real time in a physical store and instantly make optimal sales promotion proposals based on the customer emotions.

[1118] "Market data" refers to information such as market movements and trends, sales data, and consumer behavior.

[1119] "Investor information" refers to information necessary for investors to make decisions, such as stock prices, investment risks, and corporate performance.

[1120] "Past sales promotion examples" refers to information about the implementation and effectiveness of past promotions and campaigns.

[1121] "Preprocessing" refers to tasks such as data cleaning, filling in missing values, and standardizing formats to convert input data into a format that is easy to analyze.

[1122] "Feature extraction" refers to the process of finding important patterns and trends from preprocessed data that are useful for data analysis and machine learning.

[1123] "Behavioral economics" refers to a field of study that combines psychology and economics to study the decision-making motivations and behavior of consumers and investors.

[1124] Prospect theory is a theory that explains why consumers behave differently depending on whether they are gaining or losing something, and is based on differences in the evaluation of risks and benefits.

[1125] "Social proof" is a theory that explains consumer psychology, in which people base their own behavior on the behavior of others.

[1126] The "anchoring effect" is a theory that explains people's tendency to base subsequent judgments on the information they first receive.

[1127] "Emotion recognition" refers to technology that identifies a user's emotions in real time through voice analysis, text analysis, facial expression analysis, etc.

[1128] "Sales promotion proposals" refer to proposals that scientifically derive promotional campaigns and advertising messages for specific products or services in order to carry out marketing activities effectively.

[1129] In order to implement the present invention, the following system must be constructed.

[1130] First, the server has a means of receiving input market data, investor relations information, and past sales promotion cases. This means can import data in a variety of formats, such as CSV files, Excel sheets, and database connections, making it easy for users to input the data they need.

[1131] The server then has the means to preprocess the input data, cleaning it, imputing missing values, removing noise, filtering out invalid data, etc. This process can be automated using Python scripts.

[1132] Furthermore, statistical analysis, clustering, and pattern detection are performed to extract features from the preprocessed data. This allows us to understand the basic features of the data and reveal consumer behavior patterns and purchasing trends. The tools used are Python libraries (e.g., Pandas, Scikit-learn).

[1133] The system applies behavioral economics theory, such as prospect theory, social proof, and the anchoring effect, to generate sales promotion proposals based on data analysis results. This proposal generation can be achieved using an algorithm built in Python.

[1134] The invention also incorporates a means for recognizing users' emotions in real time. This involves using a camera and microphone in the smart glasses to capture the customer's facial expressions and voice, and then analyzing the data with an emotion recognition engine such as Microsoft Azure Face API. Based on the emotional data recognized at this stage, the system can customize the recommendations.

[1135] The results of this data processing and analysis are displayed on the smart glasses' display in real time, enabling prompt sales promotion proposals. Finally, the proposals output from the system can be used by users when making presentations to retailers or their internal marketing teams.

[1136] Examples:

[1137] For example, when a salesperson at a shoe store puts on smart glasses and starts serving customers, the following flow is assumed.

[1138] 1. A store clerk puts on the smart glasses and begins interacting with the customer.

[1139] 2. The smart glasses capture the customer's facial expressions and voice, and the data is sent to the server.

[1140] 3. Emotion recognition is performed in real time on the server, and the results are sent back to the smart glasses.

[1141] 4. Based on past data and behavioral economics theory, the server will suggest "new sports shoes" to customers who show positive emotions.

[1142] 5. The suggestions are displayed on the smart glasses' display, and the store clerk uses them to suggest appropriate products.

[1143] Prompt Sentence Examples

[1144] Customer sentiment analysis results: Positive

[1145] Past data analysis results: New sports shoes are effective for customers who show positive emotions

[1146] Suggestion: Recommend new sports shoes

[1147] This makes it possible for brick-and-mortar stores to instantly make optimal sales promotion proposals that reflect the customer's emotions.

[1148] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1149] Step 1:

[1150] The server receives market data, investor relations information, and past promotional examples from users in the form of CSV files, Excel spreadsheets, or database connections. The server loads this data into memory and creates an input dataset.

[1151] Step 2:

[1152] The server preprocesses the input data. This process includes data cleaning (filling in missing values, removing noise, and eliminating invalid data). Specifically, the dataset is prepared using a Python script. The input is the input data, and the output is the cleaned dataset.

[1153] Step 3:

[1154] The server converts the cleaned data into a unified format, which includes unifying date formats, normalizing numeric data, and tokenizing text data. The input is the cleaned dataset, and the output is the unified dataset.

[1155] Step 4:

[1156] The server analyzes the unified data set, calculates basic statistics, performs clustering, and detects patterns. Specifically, it performs data analysis using Python's Pandas and Scikit-learn. The input is the unified data set, and the output is the analysis results.

[1157] Step 5:

[1158] The server extracts features based on the results of data analysis. It selects important features to clarify consumer behavior patterns and purchasing trends. The input is the analysis results, and the output is the feature extraction results.

[1159] Step 6:

[1160] The server applies behavioral economics theory to the feature extraction results to generate promotional offers. Specifically, it uses an algorithm to generate offers based on prospect theory, social proof, and the anchoring effect. The input is the feature extraction results, and the output is the promotional offers.

[1161] Step 7:

[1162] The server collects data to recognize customer emotions in real time. It sends facial and voice data captured by the user through smart glasses to an emotion recognition engine such as Microsoft Azure Face API. The input is facial and voice data, and the output is the emotion recognition result.

[1163] Step 8:

[1164] The server customizes the proposal content based on the emotion recognition results. It generates optimistic proposals for customers who show positive emotions and proposals that address concerns for customers who show negative emotions. The inputs are the emotion recognition results and promotional proposals, and the output is the customized proposal content.

[1165] Step 9:

[1166] The server outputs the customized promotional offers to the display of the smart glasses, allowing the user to provide relevant offers to customers in real time. The input is the customized offer content, and the output is the offer displayed on the display of the smart glasses.

[1167] Step 10:

[1168] Based on the proposals provided by the server, users make presentations to retailers or their in-house marketing teams. The input is the proposal displayed on the smart glasses display, and the output is the actual sales promotion activity.

[1169] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1170] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1171] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1172] [Fourth embodiment]

[1173] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1174] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1176] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1177] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1180] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1181] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1182] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1184] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1185] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1186] The present invention is a system that inputs market data, investor information, past sales promotion examples, etc., preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Specific embodiments for implementing the present invention will be described below.

[1187] 1. Data input:

[1188] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[1189] 2. Data preprocessing:

[1190] The server receives the input data and performs preprocessing, including cleaning the data, standardizing the format, filling in missing values, and normalizing the data, thereby ensuring the consistency and reliability of the data.

[1191] 3. Data analysis and feature extraction:

[1192] The server then analyzes the pre-processed dataset and extracts key features using techniques such as statistical analysis, clustering, and pattern detection, which can reveal, for example, the behavioral patterns and purchasing tendencies of specific consumer groups within a target market.

[1193] 4. Application of behavioral economics theory:

[1194] The server applies behavioral economics theory to the extracted features, specifically generating promotional offers based on prospect theory, social proof, anchoring effects, etc. These offers are intended to encourage consumer behavior and motivate purchases.

[1195] 5. Generate promotional offers:

[1196] The server generates specific sales promotion proposals based on the data analysis and behavioral economics theory. These proposals include what promotional methods should be used, the reasons for using them, and the expected effects. For example, they could propose a discount campaign for the first purchase of a new health food product, or an advertising message targeted at a specific target group.

[1197] 6. Proposal Development:

[1198] The user then makes a presentation to a retailer or an in-house marketing team based on the sales promotion proposals provided by the server. The proposals are well-grounded in theoretical background and concrete data, making them highly persuasive.

[1199] Example scenario

[1200] scenario:

[1201] A user is trying to bring a new health food product to market.

[1202] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[1203] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[1204] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[1205] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[1206] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[1207] The user then uses the proposals provided by the server to make detailed presentations to retail clients and internal marketing teams.

[1208] As described above, the present invention supports the formulation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals.

[1209] The processing flow will be explained below.

[1210] Step 1:

[1211] Users use terminals to input market data, investor relations information, past sales promotion cases, etc. Data formats include CSV files, Excel sheets, and database connections.

[1212] Step 2:

[1213] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[1214] Step 3:

[1215] The server handles data formatting, including standardizing date formats, normalizing numeric data, and tokenizing text data.

[1216] Step 4:

[1217] The server normalizes the data to ensure consistency across different data sets, for example by scaling each data set to a consistent value range.

[1218] Step 5:

[1219] The server analyzes the preprocessed data set, specifically calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[1220] Step 6:

[1221] The server performs clustering to classify consumer groups based on their characteristics, for example using the K-means algorithm to group similar consumers.

[1222] Step 7:

[1223] The server performs pattern detection and analyses for trends and correlations over time, including time series analysis and calculation of correlation matrices.

[1224] Step 8:

[1225] The server extracts important features, which includes generating new features, transforming existing features, and selecting important features based on feature importance.

[1226] Step 9:

[1227] The server applies behavioral economics theories to the extracted features to generate recommendations based on prospect theory, social proof, anchoring effect, etc.

[1228] Step 10:

[1229] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[1230] Step 11:

[1231] The user receives the proposal provided by the server on the terminal and makes a presentation to the retailer or the company's internal marketing team.

[1232] Example 1

[1233] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1234] In conventional sales promotion systems, the processes of data input, preprocessing, analysis, and the generation of sales promotion proposals based on the analysis results were carried out independently, resulting in a lack of consistency and efficiency. Furthermore, it was difficult to automatically generate specific sales promotion proposals based on theories of behavioral economics, which required time and effort from the user. These issues made it difficult to develop a fast and effective sales promotion strategy.

[1235] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1236] In this invention, the server includes means for allowing a user to input market data, investor information, and past sales promotion examples using a terminal, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, and means for outputting the sales promotion proposals to the user. This makes it possible to perform the entire process from data input to the generation of sales promotion proposals as a single integrated process, enabling the formulation of a rapid and effective sales promotion strategy.

[1237] "User" refers to the person who operates the system and inputs information such as market data, investor information, and past promotional cases through a terminal.

[1238] "Terminal" refers to a device through which a user inputs data and which acts as an interface to the system.

[1239] "Market data" refers to basic information related to sales promotion, such as market trends, consumer behavior patterns, and economic indicators.

[1240] "Investor information" refers to a company's financial information, management strategy, performance forecasts, etc. provided to investors.

[1241] "Past sales promotion examples" refers to specific examples of sales promotion activities that have been implemented to date and their results.

[1242] "Server" refers to a central processing unit that pre-processes input data, performs data analysis, and generates promotional offers.

[1243] "Data preprocessing" refers to a series of processes to improve data quality, such as cleaning input data, standardizing formats, imputing missing values, and data normalization.

[1244] "Feature extraction" refers to the process of extracting important patterns and trends from pre-processed data.

[1245] "Behavioral economics" refers to theories that explain the psychological and social factors that influence human behavior and decision-making, such as prospect theory, social proof, and the anchoring effect.

[1246] "Sales promotion proposal" refers to a proposal that shows specific sales promotion methods and their effectiveness based on data analysis and behavioral economics theory.

[1247] "Output" refers to displaying the generated promotional offers to the user.

[1248] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. Detailed embodiments of this system are described below.

[1249] Hardware and software used

[1250] Users use devices to input market data, investor relations information, and past sales promotions. Devices can be PCs, tablets, smartphones, etc. Input data can be in the form of CSV files, Excel sheets, or database connections.

[1251] The server preprocesses the received data, cleaning it, standardizing its format, imputing missing values, and normalizing it, using programming languages ​​such as Python and R and libraries such as Pandas and Numpy.

[1252] Based on the preprocessed dataset, the server performs data analysis such as statistical analysis, clustering, and pattern detection using machine learning libraries such as Scikit-learn and TensorFlow.

[1253] The server applies behavioral economics theories—specifically, prospect theory, social proof, and the anchoring effect—to generate promotional offers. The proposal generation incorporates NLP (natural language processing) techniques and leverages generative AI models, such as OpenAI's GPT-3 or BERT models.

[1254] Example scenario

[1255] scenario:

[1256] Consider a case where a user is trying to bring a new health food product to market.

[1257] 1. The user uses a terminal to input past sales data for health foods, examples of competitors' sales promotions, and consumer demographic information for the target market into the system. The input data is uploaded in Excel file format.

[1258] 2. The server receives the uploaded data and performs data cleaning. If an invalid data format is detected, it is recorded in an error log and corrected as much as possible. If missing values ​​are found, they are imputed using the mean or median.

[1259] 3. The server analyzes the preprocessed dataset and extracts important features. For example, a pattern may emerge: women in their 30s tend to prefer high-protein foods. Statistical analysis and clustering then clarify trends within the target customer group.

[1260] 4. The server applies behavioral economics theory to propose strategies using discount campaigns based on prospect theory and social proof citing competitor success stories. AI models are applied to automatically generate proposals.

[1261] 5. The server generates specific sales promotion proposals such as "discount campaigns for first-time purchases of health foods" or "advertising messages for specific target groups" and outputs them to the user.

[1262] Based on the sales promotion proposals provided by the server, users can make detailed presentations to retailers and in-house marketing teams. The proposals contain both theoretical background and concrete data-based justification, making them highly persuasive.

[1263] Prompt Sentence Examples

[1264] Example 1:

[1265] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[1266] Example 2:

[1267] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[1268] Generative AI model used

[1269] The system uses generative AI models such as OpenAI's GPT-3 and BERT to generate promotional offers, leveraging advanced natural language generation capabilities to provide users with effective and persuasive promotional strategies.

[1270] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1271] Step 1:

[1272] A user uses a terminal to input market data, investor relations information, and past sales promotion cases into the system. This input data is provided as a CSV file, Excel spreadsheet, etc. For example, a user selects an Excel file and clicks the upload button on the terminal to send the data to the system.

[1273] Input: Market data, investor relations information, and past promotions provided in the form of CSV files, Excel sheets, database connections, etc.

[1274] Output: Input data sent to the server

[1275] Step 2:

[1276] The server preprocesses the data received. Specifically, it performs processes such as data cleaning, format standardization, missing value imputation, and data normalization. If an invalid data format is detected, it records it in the error log and attempts to correct it if possible. If missing values ​​are found, they are imputed with the mean or median.

[1277] Input: Input data sent by the user

[1278] Output: Cleaned and uniformly formatted pre-processed data

[1279] Step 3:

[1280] The server analyzes the preprocessed data. Analysis methods include statistical analysis, clustering, and pattern detection. This reveals patterns of consumer behavior and market trends. For example, the server might extract a pattern that women in their 30s prefer high-protein foods.

[1281] Input: Preprocessed data

[1282] Output: Analysis results and important feature data

[1283] Step 4:

[1284] The server applies behavioral economics theory based on the analysis results. For example, it uses prospect theory, social proof, and the anchoring effect to generate effective sales promotion proposals. It utilizes generative AI models to automatically propose strategies to encourage consumer behavior.

[1285] Input: Analysis results and important feature data

[1286] Output: Sales promotion proposals based on the theory of behavioral economics

[1287] Step 5:

[1288] The server outputs the generated sales promotion proposal to the user. This proposal includes the promotional method to be used, the reasons for it, and the expected effects. The user then uses this proposal to make a presentation to a retailer or an internal marketing team. For example, the server might propose a "discount campaign for the first purchase of health foods" and simulate its effects.

[1289] Input: Sales promotion proposals based on the theory of behavioral economics

[1290] Output: Promotional offers provided to the user

[1291] Prompt Sentence Examples

[1292] Example 1:

[1293] "Please suggest the optimal sales promotion strategy for introducing a new health food product to the market. Based on past sales data and competitive information, we are targeting women in their 30s."

[1294] Example 2:

[1295] "Generate effective advertising messages for your target market. We especially look for strategies that utilize prospect theory and social proof."

[1296] (Application example 1)

[1297] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1298] While conventional sales promotion proposal systems are useful in generating proposals based on data analysis and behavioral economics theory, they lack a means to directly provide proposals based on consumer behavior and purchasing trends in real time. As a result, it is difficult to carry out immediate sales promotion activities in stores, and sales promotions cannot be carried out at the optimal time.

[1299] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1300] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals in real time, and means for outputting sales promotion proposals based on consumer behavior and purchasing trends in real time using a smart device. This makes it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[1301] "Market data" refers to information about market trends, competitive situations, consumer preferences and purchasing patterns, etc.

[1302] "Investor relations information" refers to information about a company's performance and strategies that is provided to investors.

[1303] "Past sales promotion cases" is information about the content and results of sales promotion activities carried out in the past.

[1304] "Data preprocessing" is the process of converting raw data into an analyzable form, including data cleaning, imputation of missing values, and normalization.

[1305] "Feature extraction" is the process of finding significant patterns and trends in a data set.

[1306] "Behavioral economics" is a science that analyzes economic behavior by taking into account psychological factors and is a theory that influences consumer decision-making.

[1307] "Prospect theory" is a theory that explains how people make decisions in risky situations.

[1308] "Social proof" is a psychological phenomenon in which people base their own behavior on the behavior of others.

[1309] The "anchoring effect" is a phenomenon in which the first information presented has a strong influence on subsequent decision-making.

[1310] "Real-time" means that processing is done instantly and results are obtained almost immediately.

[1311] "Sales promotion proposals" are specific methods and strategies for increasing consumer purchasing motivation.

[1312] A "smart device" is a device that has internet connectivity and can process and display a variety of information.

[1313] The present invention is a system that inputs market data, investor information, and past sales promotion cases, preprocesses, analyzes, and extracts features from the data, and generates sales promotion proposals based on the theory of behavioral economics. A detailed description of an embodiment of the present invention will be given below.

[1314] The system consists of the following stages:

[1315] 1. Data input

[1316] Users use terminals to input market data, investor relations information, and past promotions into the system, which is provided via CSV files, Excel sheets, or database connections.

[1317] 2. Data Preprocessing

[1318] The server receives the input data and performs preprocessing, which includes data cleaning, formatting standardization, missing value imputation, and data normalization. Specifically, data cleaning is performed using the Python Pandas library, and data normalization is performed using Scikit-learn.

[1319] 3. Data analysis and feature extraction

[1320] The server analyzes the pre-processed dataset and extracts key features using statistical analysis, clustering (e.g., K-means), and pattern detection. This process identifies behavioral patterns and purchasing trends among consumer groups.

[1321] 4. Application of behavioral economics theory

[1322] The server applies behavioral economics theory to the extracted features, specifically prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer behavior and increase purchasing intent.

[1323] 5. Generate promotional offers

[1324] The server generates specific sales promotion proposals based on the above data analysis and behavioral economics theory. These proposals are output in real time via smart devices (e.g., smart glasses). For example, if a store clerk is wearing smart glasses, appropriate sales promotion proposals will be instantly displayed based on the customer's behavioral patterns.

[1325] 6. Proposal Development

[1326] Users can carry out sales promotion activities in real time at the store based on sales promotion proposals provided by the server. In a specific example, a store clerk wearing smart glasses receives a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately provides that information to the customer.

[1327] Prompt Sentence Examples

[1328] "Generate real-time promotional offers using the following data:

[1329] Market Data

[1330] Investor information

[1331] Past promotional examples

[1332] The generated recommendations should be based on behavioral economics theory (e.g., prospect theory). They should demonstrate effectiveness for specific consumer groups and provide specific examples of sales strategies. The output should be in the following format:

[1333] {

[1334] "promotion_type": "discount",

[1335] "message": "Your 10% discount on our new protein bars is valid.",

[1336] "expected_effect": "Increased willingness to purchase"

[1337] }

[1338] "

[1339] As a result, the present invention systemizes a series of processes from data input to proposal creation and deployment, making it possible to instantly provide optimal sales promotion proposals at the store and maximize sales effectiveness.

[1340] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1341] Step 1:

[1342] Users use a terminal to input market data, investor relations information, and past promotions. Specifically, they upload the data to the system via a CSV file, Excel spreadsheet, or database connection. The input of this process is market data, investor relations information, and past promotions, and the output is that this data is stored on the server.

[1343] Step 2:

[1344] The server receives the input data and performs preprocessing. Specifically, it performs the following data processing: data cleaning, format standardization, missing value imputation, and data normalization. For example, it uses the Pandas library to impute missing values ​​and Scikit-learn to normalize the data. The input of this process is the input raw data, and the output is cleaned and normalized data.

[1345] Step 3:

[1346] The server analyzes the preprocessed data and extracts features. Specifically, it performs statistical analysis and clustering (e.g., K-means) to identify behavioral patterns and purchasing tendencies of consumer groups. For example, K-means clustering is used to identify target groups. The input of this process is the preprocessed data, and the output is consumer behavior patterns and features.

[1347] Step 4:

[1348] The server applies behavioral economics theory to the extracted features. Specifically, it generates recommendations using prospect theory, social proof, and the anchoring effect. For example, it uses prospect theory to recommend a "limited-time discount." The input to this process is the extracted feature data, and the output is a recommendation based on behavioral economics.

[1349] Step 5:

[1350] The server generates specific sales promotion proposals based on the theory of behavioral economics. The proposals include plans to be output in real time via smart devices (e.g., smart glasses). Specifically, the server outputs the generated sales promotion proposals in JSON format and sends them to the smart devices. The input of this process is the proposals based on behavioral economics, and the output is the real-time sales promotion proposals.

[1351] Step 6:

[1352] Based on the sales promotion proposals provided by the server, users can carry out sales promotion activities in real time at the store. For example, a sales clerk wearing smart glasses can receive a proposal such as "This woman in her 30s is eligible for a 10% discount on our new protein bar," and immediately convey that information to the customer. The input to this process is the real-time sales promotion proposal sent from the server, and the output is the implementation of the sales promotion activity for the customer.

[1353] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1354] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments for implementing the present invention will be described below.

[1355] 1. Data input:

[1356] Users use terminals to input market data, investor relations information, and past promotions into the system, which can be provided in the form of CSV files, Excel spreadsheets, or database connections.

[1357] 2. Data preprocessing:

[1358] The server receives the input data and performs data cleaning, specifically, imputing missing values, removing noise, and eliminating invalid data.

[1359] 3. Standardize data formats:

[1360] The server unifies the data format by unifying date formats, standardizing numeric data, tokenizing text data, etc.

[1361] 4. Data normalization:

[1362] The server normalizes the preprocessed data to ensure consistency across different datasets, for example by scaling each data set to a uniform value range.

[1363] 5. Data analysis and feature extraction:

[1364] The server analyzes the preprocessed dataset and performs basic statistical calculations, clustering, pattern detection, etc. to understand the basic characteristics of the data. It selects important features and reveals consumer behavior patterns and purchasing trends.

[1365] 6. Application of behavioral economics theory:

[1366] The server generates suggestions based on the extracted features, such as prospect theory, social proof, and anchoring effect, which can encourage consumer behavior and increase purchasing motivation.

[1367] 7. Incorporating an Emotion Engine:

[1368] The server recognizes the user's emotions using an emotion engine. The emotion engine detects the user's emotions using at least one of voice analysis, text analysis, and facial expression analysis. For example, the server collects real-time emotion data while the user is giving a presentation.

[1369] 8. Leveraging Emotional Data:

[1370] The server customizes the suggestions based on the user's emotional data, recognized by the emotion engine. If the user is expressing positive emotions, the server emphasizes optimistic suggestions. Conversely, if the user is expressing negative emotions, the server adds information to address concerns.

[1371] 9. Promotional Offer Generation:

[1372] The server generates specific promotional proposals based on the data analysis, application of behavioral economics theory, and sentiment data, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[1373] 10. Proposal Development:

[1374] The user receives the proposals provided by the server on their device and makes presentations to retailers or their internal marketing teams. The proposals are customized based on emotional data, making them more persuasive to the target audience.

[1375] Example scenario

[1376] scenario:

[1377] A user is trying to bring a new health food product to market.

[1378] Users use a terminal to input past health food sales data, competitor promotional cases, and consumer demographic information for the target market into the system.

[1379] The server performs data cleaning, imputes missing values, and normalizes different datasets into a unified format.

[1380] The server analyzes health food purchasing patterns and consumer preferences based on past success stories and market trends, extracting characteristics such as "women in their 30s particularly like high-protein foods."

[1381] Sarver applies prospect theory to propose a strategy of offering a new health food product at a discounted price for a limited time. He also cites competitors' success stories as social proof to increase the credibility of his product.

[1382] The server generates specific proposals for a "discount campaign for the first purchase of health foods," a display method, and an advertising message.

[1383] The server uses an emotion engine to collect real-time emotional data from users during a presentation. For example, if a user has a positive reaction, the server can emphasize the content of the proposal in line with that emotion.

[1384] The user then uses the server-provided customized proposal to make detailed presentations to retailers and internal marketing teams.

[1385] As described above, the present invention supports the creation of effective sales promotion strategies by systematizing a series of processes from data input to the creation and deployment of proposals and by customizing them based on the user's emotions.

[1386] The processing flow will be explained below.

[1387] Step 1:

[1388] Users use terminals to input market data, investor relations information, and past promotional cases into the system, which can be provided in the form of CSV files, Excel spreadsheets, database connections, etc.

[1389] Step 2:

[1390] The server receives the input data and performs data cleaning, specifically by completing missing values, removing noise, and eliminating invalid data to improve the quality of the data.

[1391] Step 3:

[1392] The server handles data formatting, including standardizing date formats, standardizing numeric data, and tokenizing text data.

[1393] Step 4:

[1394] The server normalizes the data, scaling each data set to a consistent value range for consistency across different data sets.

[1395] Step 5:

[1396] The server analyzes the preprocessed dataset, calculating basic statistics such as the mean, median, and variance to understand the basic characteristics of the data.

[1397] Step 6:

[1398] The server performs clustering to classify consumer groups based on their characteristics, specifically by using the K-means algorithm to group similar consumers.

[1399] Step 7:

[1400] The server performs pattern detection, analyzing trends and correlations over time, and uncovering hidden patterns in the data through time series analysis and calculation of correlation matrices.

[1401] Step 8:

[1402] The server extracts important features, generates new features, transforms existing features, and selects the most important features using Feature Importance.

[1403] Step 9:

[1404] The server applies behavioral economics theories, such as prospect theory, social proof, and the anchoring effect, to generate recommendations that drive consumer action.

[1405] Step 10:

[1406] The server recognizes the user's emotions using an emotion engine, which detects the user's emotions using voice analysis, text analysis, or facial expression analysis.

[1407] Step 11:

[1408] The server customizes the suggestions based on the user's emotional data. For example, if the user is expressing positive emotions, it will emphasize optimistic information, and if the user is expressing negative emotions, it will provide information that emphasizes safety and reliability.

[1409] Step 12:

[1410] The server generates specific promotional proposals, including designing promotional campaigns, creating advertising messages, and optimizing product placement in stores and online stores.

[1411] Step 13:

[1412] The user receives the proposal information provided by the server on their device and makes a presentation to their retailer or in-house marketing team. The proposal information is customized based on emotional data, making it more persuasive to the target audience.

[1413] Example 2

[1414] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1415] Conventional sales promotion systems are limited to simple data analysis, and have limitations in predicting consumer behavior and generating effective proposals. Furthermore, proposals lack persuasiveness and effectiveness because they are not customized to take user emotions into account. To solve this problem, a system is needed that precisely analyzes input data, generates proposals based on theories of behavioral economics, and further customizes proposals by recognizing user emotions in real time.

[1416] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting market data, investor information, and past sales promotion cases and preprocessing the data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for recognizing user emotions and customizing the sales promotion proposals, and means for outputting the customized sales promotion proposals. This makes it possible to generate advanced and effective sales promotion proposals based on the input data and further customize the proposals according to the user's emotions.

[1417] "Market data" is information about market movements, trends, sales, consumer behavior, etc.

[1418] "Investor relations information" refers to information provided to investors, such as a company's financial situation, performance forecasts, and investment risks.

[1419] "Sales promotion cases" refers to information about the content, results, effects, etc. of sales promotion activities that have been carried out in the past.

[1420] "Data preprocessing" is the process of preparing input data for analysis by filling in missing values, removing noise, and excluding invalid data.

[1421] "Feature extraction" is a data analysis technique for finding useful patterns and trends in pre-processed data.

[1422] "Behavioral economics theory" is a theory that explains human psychology and behavior in economic activities, and includes prospect theory, social proof, and the anchoring effect.

[1423] A "sales promotion proposal" is a concrete presentation of strategies and ideas for promoting sales.

[1424] "Means for recognizing emotions" refers to technology that detects a user's emotions using voice analysis, text analysis, facial expression analysis, etc.

[1425] "Means for customizing suggestions" refers to technology that adjusts and adapts suggestions based on the user's emotional data.

[1426] "Data analysis" refers to techniques such as statistical analysis and clustering that are used to extract useful information from data.

[1427] "Statistical analysis" is a statistical method for understanding the distribution and trends of data.

[1428] "Clustering" is an analytical technique for classifying data into similar groups.

[1429] "Prospect theory" is a theory that explains how people evaluate gains and losses.

[1430] "Social proof" is a psychological phenomenon in which people base their decisions on the behavior and success stories of others.

[1431] The "anchoring effect" is a phenomenon in which initially presented information has a strong influence on subsequent decision-making.

[1432] The present invention is a system that inputs market data, investor information, and past sales promotion examples, preprocesses, analyzes, and extracts features from the data, generates sales promotion proposals based on the theory of behavioral economics, and further combines this with an emotion engine that recognizes user emotions. Specific embodiments of the present invention are described below.

[1433] 1. Data input

[1434] Users use a terminal to input market data, investor relations information, and past sales promotions into the system. Input data can be provided in the form of CSV files, Excel spreadsheets, or database connections, allowing users to easily utilize existing data resources to provide data to the system.

[1435] 2. Data Preprocessing

[1436] The server receives the input data and performs data cleaning using the Python Pandas library. Specifically, it imputes missing values, removes noise, and eliminates invalid data. This preprocessing step improves the quality of the data and increases the reliability of the subsequent analysis results.

[1437] 3. Standardization of data formats

[1438] The server standardizes the date format of the cleaned data to "YYYY-MM-DD" and uses Scikit-learn's scaling library to normalize numeric data. It also uses NLP tools to tokenize text data and convert it into a unified format, making the data consistent and easier to analyze.

[1439] 4. Data Normalization

[1440] The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1. This normalization step ensures consistency between different datasets, making them easier to compare.

[1441] 5. Data analysis and feature extraction

[1442] The server analyzes the preprocessed dataset, calculates basic statistics, and uses clustering algorithms (e.g., K-means clustering) to detect patterns and identify consumer behavior and purchasing trends. It then selects important features to help predict consumer behavior and develop marketing strategies.

[1443] 6. Application of behavioral economics theory

[1444] The server applies behavioral economics theories such as prospect theory, social proof, and anchoring effect to generate sales promotion proposals for the extracted features. For example, it is possible to stimulate consumer purchasing motivation by proposing a "limited-time discount promotion."

[1445] 7. Incorporating and utilizing an emotional engine

[1446] The server recognizes the user's emotions using an emotion engine. The emotion engine detects emotions in real time using voice analysis, text analysis, or facial expression analysis. The server customizes the suggestions based on the user's emotion data, emphasizing optimistic suggestions when the user shows positive emotions, and adding information to cover concerns when the user shows negative emotions.

[1447] 8. Promotional proposal generation and deployment

[1448] The server generates sales promotion proposals based on data analysis, behavioral economics theory, and emotional data. Specific examples include campaign design, advertising message creation, and product placement optimization. Users receive the proposals provided by the server on their devices and present them to clients or their internal marketing teams. Customized proposals based on emotional data can increase persuasiveness.

[1449] Example scenario

[1450] If a user is trying to bring a new health food product to market, the following prompt text could be used:

[1451] Example prompt sentence:

[1452] "Generate a sales promotion strategy for a high-protein food product targeted at women in their 30s. Using past sales data and competitor examples as a reference, create a proposal by applying prospect theory."

[1453] As described above, the present invention supports the development of more effective sales promotion strategies by systematizing a series of processes from data input to proposal creation and development, and by customizing based on the user's emotions.

[1454] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1455] Step 1:

[1456] Input: Users use terminals to upload market data, investor relations information, and past promotional cases into the system.

[1457] Specific operation: The user selects a CSV file or Excel sheet on the device and clicks the "Import" button.

[1458] Output: The server receives the input data and stores it in its internal database.

[1459] Step 2:

[1460] Input: The server retrieves the input data.

[1461] Specific operation: The server reads data from the database and performs data cleaning using Python's Pandas library.

[1462] Output: Cleaned data with missing values ​​imputed and noise and incorrect data removed.

[1463] Step 3:

[1464] Input: Cleaned data.

[1465] What it does: The server standardizes the date format to "YYYY-MM-DD", applies Scikit-learn's scaling library to normalize numeric data, and tokenizes text data using NLP tools.

[1466] Output: Uniformly formatted data.

[1467] Step 4:

[1468] Input: Uniformly formatted data.

[1469] What it does: The server uses Scikit-learn's MinMaxScaler to scale all data to the range 0 to 1.

[1470] Output: Normalized data.

[1471] Step 5:

[1472] Input: Normalized data.

[1473] What it does: The server calculates basic statistics and uses the K-means clustering algorithm to find patterns in the data.

[1474] Output: Clustering results and feature extracted data.

[1475] Step 6:

[1476] Input: Feature extracted data.

[1477] What happens: The server applies prospect theory, social proof, and anchoring effects to generate promotional offers.

[1478] Output: Promotion proposal.

[1479] Step 7:

[1480] Input: Promotion offers and user interaction data.

[1481] How it works: The server uses an emotion engine to recognize the user's emotions in real time, using either voice analysis, text analysis, or facial expression analysis.

[1482] Output: User emotion data.

[1483] Step 8:

[1484] Input: Promotional offers and user sentiment data.

[1485] What happens: The server customizes promotional offers based on the user's emotions.

[1486] Output: A customized promotional offer.

[1487] Step 9:

[1488] Input: Customized promotional offer.

[1489] Specific operations: The server generates detailed specific proposals such as campaign design, advertising message creation, and product placement optimization.

[1490] Output: Final promotion proposal.

[1491] Step 10:

[1492] Input: Final promotion proposal.

[1493] Specific operation: The user receives the proposal from the server and uses the terminal to present it to clients or the internal marketing team.

[1494] Output: A customized promotional offer for presentation.

[1495] (Application example 2)

[1496] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1497] Conventional sales promotion systems were unable to analyze customer emotions and behavior in real time and make immediate proposals based on that analysis. This made it difficult to provide optimal sales strategies tailored to customer needs and emotions in a timely manner, limiting the effectiveness of sales promotions. In particular, in brick-and-mortar stores, it is necessary to quickly and accurately understand the emotions of each individual customer and make proposals based on that information, making it urgent to solve this problem.

[1498] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1499] In this invention, the server includes means for receiving input market data, investor information, and past sales promotion examples, means for preprocessing the input data, means for extracting features from the preprocessed data, means for generating sales promotion proposals for the extracted features by applying the theory of behavioral economics, means for outputting the sales promotion proposals, means for recognizing customer emotions in real time, and means for customizing the proposal content based on the recognized emotion data. This makes it possible to grasp customer emotions in real time in a physical store and instantly make optimal sales promotion proposals based on the customer emotions.

[1500] "Market data" refers to information such as market movements and trends, sales data, and consumer behavior.

[1501] "Investor information" refers to information necessary for investors to make decisions, such as stock prices, investment risks, and corporate performance.

[1502] "Past sales promotion examples" refers to information about the implementation and effectiveness of past promotions and campaigns.

[1503] "Preprocessing" refers to tasks such as data cleaning, filling in missing values, and standardizing formats to convert input data into a format that is easy to analyze.

[1504] "Feature extraction" refers to the process of finding important patterns and trends from preprocessed data that are useful for data analysis and machine learning.

[1505] "Behavioral economics" refers to a field of study that combines psychology and economics to study the decision-making motivations and behavior of consumers and investors.

[1506] Prospect theory is a theory that explains why consumers behave differently depending on whether they are gaining or losing something, and is based on differences in the evaluation of risks and benefits.

[1507] "Social proof" is a theory that explains consumer psychology, in which people base their own behavior on the behavior of others.

[1508] The "anchoring effect" is a theory that explains people's tendency to base subsequent judgments on the information they first receive.

[1509] "Emotion recognition" refers to technology that identifies a user's emotions in real time through voice analysis, text analysis, facial expression analysis, etc.

[1510] "Sales promotion proposals" refer to proposals that scientifically derive promotional campaigns and advertising messages for specific products or services in order to carry out marketing activities effectively.

[1511] In order to implement the present invention, the following system must be constructed.

[1512] First, the server has a means of receiving input market data, investor relations information, and past sales promotion cases. This means can import data in a variety of formats, such as CSV files, Excel sheets, and database connections, making it easy for users to input the data they need.

[1513] The server then has the means to preprocess the input data, cleaning it, imputing missing values, removing noise, filtering out invalid data, etc. This process can be automated using Python scripts.

[1514] Furthermore, statistical analysis, clustering, and pattern detection are performed to extract features from the preprocessed data. This allows us to understand the basic features of the data and reveal consumer behavior patterns and purchasing trends. The tools used are Python libraries (e.g., Pandas, Scikit-learn).

[1515] The system applies behavioral economics theory, such as prospect theory, social proof, and the anchoring effect, to generate sales promotion proposals based on data analysis results. This proposal generation can be achieved using an algorithm built in Python.

[1516] The invention also incorporates a means for recognizing users' emotions in real time. This involves using a camera and microphone in the smart glasses to capture the customer's facial expressions and voice, and then analyzing the data with an emotion recognition engine such as Microsoft Azure Face API. Based on the emotional data recognized at this stage, the system can customize the recommendations.

[1517] The results of this data processing and analysis are displayed on the smart glasses' display in real time, enabling prompt sales promotion proposals. Finally, the proposals output from the system can be used by users when making presentations to retailers or their internal marketing teams.

[1518] Examples:

[1519] For example, when a salesperson at a shoe store puts on smart glasses and starts serving customers, the following flow is assumed.

[1520] 1. A store clerk puts on the smart glasses and begins interacting with the customer.

[1521] 2. The smart glasses capture the customer's facial expressions and voice, and the data is sent to the server.

[1522] 3. Emotion recognition is performed in real time on the server, and the results are sent back to the smart glasses.

[1523] 4. Based on past data and behavioral economics theory, the server will suggest "new sports shoes" to customers who show positive emotions.

[1524] 5. The suggestions are displayed on the smart glasses' display, and the store clerk uses them to suggest appropriate products.

[1525] Prompt Sentence Examples

[1526] Customer sentiment analysis results: Positive

[1527] Past data analysis results: New sports shoes are effective for customers who show positive emotions

[1528] Suggestion: Recommend new sports shoes

[1529] This makes it possible for brick-and-mortar stores to instantly make optimal sales promotion proposals that reflect the customer's emotions.

[1530] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1531] Step 1:

[1532] The server receives market data, investor relations information, and past promotional examples from users in the form of CSV files, Excel spreadsheets, or database connections. The server loads this data into memory and creates an input dataset.

[1533] Step 2:

[1534] The server preprocesses the input data. This process includes data cleaning (filling in missing values, removing noise, and eliminating invalid data). Specifically, the dataset is prepared using a Python script. The input is the input data, and the output is the cleaned dataset.

[1535] Step 3:

[1536] The server converts the cleaned data into a unified format, which includes unifying date formats, normalizing numeric data, and tokenizing text data. The input is the cleaned dataset, and the output is the unified dataset.

[1537] Step 4:

[1538] The server analyzes the unified data set, calculates basic statistics, performs clustering, and detects patterns. Specifically, it performs data analysis using Python's Pandas and Scikit-learn. The input is the unified data set, and the output is the analysis results.

[1539] Step 5:

[1540] The server extracts features based on the results of data analysis. It selects important features to clarify consumer behavior patterns and purchasing trends. The input is the analysis results, and the output is the feature extraction results.

[1541] Step 6:

[1542] The server applies behavioral economics theory to the feature extraction results to generate promotional offers. Specifically, it uses an algorithm to generate offers based on prospect theory, social proof, and the anchoring effect. The input is the feature extraction results, and the output is the promotional offers.

[1543] Step 7:

[1544] The server collects data to recognize customer emotions in real time. It sends facial and voice data captured by the user through smart glasses to an emotion recognition engine such as Microsoft Azure Face API. The input is facial and voice data, and the output is the emotion recognition result.

[1545] Step 8:

[1546] The server customizes the proposal content based on the emotion recognition results. It generates optimistic proposals for customers who show positive emotions and proposals that address concerns for customers who show negative emotions. The inputs are the emotion recognition results and promotional proposals, and the output is the customized proposal content.

[1547] Step 9:

[1548] The server outputs the customized promotional offers to the display of the smart glasses, allowing the user to provide relevant offers to customers in real time. The input is the customized offer content, and the output is the offer displayed on the display of the smart glasses.

[1549] Step 10:

[1550] Based on the proposals provided by the server, users make presentations to retailers or their in-house marketing teams. The input is the proposal displayed on the smart glasses display, and the output is the actual sales promotion activity.

[1551] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1552] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1553] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1554] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1555] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1556] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1557] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1558] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1559] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1560] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1561] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1562] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1563] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1564] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1565] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1566] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1567] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1568] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1569] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1570] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1571] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1572] The following is further disclosed regarding the above embodiment.

[1573] (Claim 1)

[1574] A means of receiving input market data, investor information, and past promotional examples;

[1575] means for preprocessing the input data;

[1576] means for extracting features from the preprocessed data;

[1577] a means for applying theories of behavioral economics to generate promotional offers for the extracted features;

[1578] means for outputting said promotional offers;

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system of claim 1, further comprising means for analyzing the preprocessed data, performing statistical analysis and clustering, and detecting patterns.

[1582] (Claim 3)

[1583] 2. The system of claim 1, wherein the theories of behavioral economics include prospect theory, social proof, and anchoring effect.

[1584] "Example 1"

[1585] (Claim 1)

[1586] a means for a user to input market data, investor relations information, and past promotional examples using the terminal;

[1587] A means for the server to preprocess the input data;

[1588] means for the server to extract features from the preprocessed data;

[1589] means for the server to generate promotional offers for the extracted features by applying theories of behavioral economics;

[1590] means by the server to output promotional offers to the user;

[1591] A system including:

[1592] (Claim 2)

[1593] 10. The system of claim 1, wherein the server further comprises means for analyzing the preprocessed data, performing statistical analysis and clustering, and detecting patterns.

[1594] (Claim 3)

[1595] 2. The system of claim 1, wherein the theories of behavioral economics include prospect theory, social proof, and the anchoring effect.

[1596] "Application Example 1"

[1597] (Claim 1)

[1598] A means of receiving input market data, investor information, and past promotional examples;

[1599] means for preprocessing the input data;

[1600] means for extracting features from the preprocessed data;

[1601] a means for applying theories of behavioral economics to generate promotional offers for the extracted features;

[1602] means for outputting said promotional offers in real time;

[1603] A system including:

[1604] (Claim 2)

[1605] 10. The system of claim 1, further comprising means for analyzing the preprocessed data, performing statistical analysis and clustering, and detecting patterns.

[1606] (Claim 3)

[1607] 2. The system of claim 1, wherein the theories of behavioral economics include prospect theory, social proof, and anchoring effect.

[1608] (Claim 4)

[1609] 10. The system of claim 1, further comprising means for utilizing the smart device to output promotional offers based on consumer behavior and purchasing trends in real time.

[1610] (Claim 5)

[1611] 10. The system of claim 1, wherein the promotional suggestions include prompt sentences generated using a generative AI model.

[1612] "Example 2: Combining Emotion Engines"

[1613] (Claim 1)

[1614] A means of receiving input market data, investor information, and past promotional examples;

[1615] means for preprocessing the input data;

[1616] means for extracting features from the preprocessed data;

[1617] a means for applying theories of behavioral economics to generate promotional offers for the extracted features;

[1618] means for recognizing user emotions and customizing said promotional offers;

[1619] means for outputting the customized promotional offers;

[1620] A system including:

[1621] (Claim 2)

[1622] 10. The system of claim 1, further comprising means for analyzing the preprocessed data, performing statistical analysis and clustering, and detecting patterns.

[1623] (Claim 3)

[1624] 2. The system of claim 1, wherein the theories of behavioral economics include prospect theory, social proof, anchoring effect, and applications thereof.

[1625] "Application example 2 when combining emotion engines"

[1626] (Claim 1)

[1627] A means of receiving input market data, investor information, and past promotional examples;

[1628] means for preprocessing the input data;

[1629] means for extracting features from the preprocessed data;

[1630] a means for applying theories of behavioral economics to generate promotional offers for the extracted features;

[1631] means for outputting said promotional offers;

[1632] A means of recognizing customer sentiment in real time,

[1633] A means to customize suggestions based on the recognized emotion data; and

[1634] A system including:

[1635] (Claim 2)

[1636] 10. The system of claim 1, further comprising means for analyzing the preprocessed data, performing statistical analysis and clustering, and detecting patterns.

[1637] (Claim 3)

[1638] 2. The system of claim 1, wherein the theories of behavioral economics include prospect theory, social proof, and anchoring effect. [Explanation of symbols]

[1639] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving input market data, investor information, and past promotional examples; means for preprocessing the input data; means for extracting features from the preprocessed data; a means for applying theories of behavioral economics to generate promotional offers for the extracted features; means for outputting said promotional offers; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the pre-processed data, performing statistical analysis and clustering, and detecting patterns.

3. The system of claim 1 , wherein the theories of behavioral economics include prospect theory, social proof, and anchoring effect.

Images